parent
ce1a29964a
commit
8489d8b38e
@ -0,0 +1,86 @@
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
pip-wheel-metadata/
|
||||
share/python-wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
MANIFEST
|
||||
|
||||
# PyInstaller
|
||||
build/
|
||||
dist/
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.nox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*.cover
|
||||
.hypothesis/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
db.sqlite3
|
||||
db.sqlite3-journal
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
target/
|
||||
|
||||
# Jupyter Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# IPython
|
||||
profile_default/
|
||||
ipython_config.py
|
||||
|
||||
# pyenv
|
||||
.python-version
|
||||
|
||||
# pipenv
|
||||
.Pipfile.lock
|
||||
|
||||
runs/
|
||||
@ -0,0 +1,67 @@
|
||||
import torch
|
||||
import numpy as np
|
||||
from models.experimental import attempt_load
|
||||
from utils.general import non_max_suppression, scale_coords
|
||||
from utils.BaseDetector import baseDet
|
||||
from utils.torch_utils import select_device
|
||||
from utils.datasets import letterbox
|
||||
|
||||
class Detector(baseDet):
|
||||
|
||||
def __init__(self):
|
||||
super(Detector, self).__init__()
|
||||
self.init_model()
|
||||
self.build_config()
|
||||
|
||||
def init_model(self):
|
||||
|
||||
self.weights = 'weights/yolov5s.pt'
|
||||
self.device = '0' if torch.cuda.is_available() else 'cpu'
|
||||
self.device = select_device(self.device)
|
||||
model = attempt_load(self.weights, map_location=self.device)
|
||||
model.to(self.device).eval()
|
||||
model.float()
|
||||
# torch.save(model, 'test.pt')
|
||||
self.m = model
|
||||
self.names = model.module.names if hasattr(
|
||||
model, 'module') else model.names
|
||||
|
||||
def preprocess(self, img):
|
||||
|
||||
img0 = img.copy()
|
||||
img = letterbox(img, new_shape=self.img_size)[0]
|
||||
img = img[:, :, ::-1].transpose(2, 0, 1)
|
||||
img = np.ascontiguousarray(img)
|
||||
img = torch.from_numpy(img).to(self.device)
|
||||
img = img.half() # 半精度
|
||||
img /= 255.0 # 图像归一化
|
||||
if img.ndimension() == 3:
|
||||
img = img.unsqueeze(0)
|
||||
|
||||
return img0, img
|
||||
|
||||
def detect(self, im):
|
||||
|
||||
im0, img = self.preprocess(im)
|
||||
pred = self.m(img.float(), augment=False)[0]
|
||||
pred = pred.float()
|
||||
pred = non_max_suppression(pred, self.threshold, 0.4)
|
||||
|
||||
pred_boxes = []
|
||||
for det in pred:
|
||||
|
||||
if det is not None and len(det):
|
||||
det[:, :4] = scale_coords(
|
||||
img.shape[2:], det[:, :4], im0.shape).round()
|
||||
|
||||
for *x, conf, cls_id in det:
|
||||
lbl = self.names[int(cls_id)]
|
||||
if not lbl in ['person', 'car', 'truck']:
|
||||
continue
|
||||
x1, y1 = int(x[0]), int(x[1])
|
||||
x2, y2 = int(x[2]), int(x[3])
|
||||
pred_boxes.append(
|
||||
(x1, y1, x2, y2, lbl, conf))
|
||||
|
||||
return im, pred_boxes
|
||||
|
||||
@ -0,0 +1,674 @@
|
||||
GNU GENERAL PUBLIC LICENSE
|
||||
Version 3, 29 June 2007
|
||||
|
||||
Copyright (C) 2007 Free Software Foundation, Inc. <http://fsf.org/>
|
||||
Everyone is permitted to copy and distribute verbatim copies
|
||||
of this license document, but changing it is not allowed.
|
||||
|
||||
Preamble
|
||||
|
||||
The GNU General Public License is a free, copyleft license for
|
||||
software and other kinds of works.
|
||||
|
||||
The licenses for most software and other practical works are designed
|
||||
to take away your freedom to share and change the works. By contrast,
|
||||
the GNU General Public License is intended to guarantee your freedom to
|
||||
share and change all versions of a program--to make sure it remains free
|
||||
software for all its users. We, the Free Software Foundation, use the
|
||||
GNU General Public License for most of our software; it applies also to
|
||||
any other work released this way by its authors. You can apply it to
|
||||
your programs, too.
|
||||
|
||||
When we speak of free software, we are referring to freedom, not
|
||||
price. Our General Public Licenses are designed to make sure that you
|
||||
have the freedom to distribute copies of free software (and charge for
|
||||
them if you wish), that you receive source code or can get it if you
|
||||
want it, that you can change the software or use pieces of it in new
|
||||
free programs, and that you know you can do these things.
|
||||
|
||||
To protect your rights, we need to prevent others from denying you
|
||||
these rights or asking you to surrender the rights. Therefore, you have
|
||||
certain responsibilities if you distribute copies of the software, or if
|
||||
you modify it: responsibilities to respect the freedom of others.
|
||||
|
||||
For example, if you distribute copies of such a program, whether
|
||||
gratis or for a fee, you must pass on to the recipients the same
|
||||
freedoms that you received. You must make sure that they, too, receive
|
||||
or can get the source code. And you must show them these terms so they
|
||||
know their rights.
|
||||
|
||||
Developers that use the GNU GPL protect your rights with two steps:
|
||||
(1) assert copyright on the software, and (2) offer you this License
|
||||
giving you legal permission to copy, distribute and/or modify it.
|
||||
|
||||
For the developers' and authors' protection, the GPL clearly explains
|
||||
that there is no warranty for this free software. For both users' and
|
||||
authors' sake, the GPL requires that modified versions be marked as
|
||||
changed, so that their problems will not be attributed erroneously to
|
||||
authors of previous versions.
|
||||
|
||||
Some devices are designed to deny users access to install or run
|
||||
modified versions of the software inside them, although the manufacturer
|
||||
can do so. This is fundamentally incompatible with the aim of
|
||||
protecting users' freedom to change the software. The systematic
|
||||
pattern of such abuse occurs in the area of products for individuals to
|
||||
use, which is precisely where it is most unacceptable. Therefore, we
|
||||
have designed this version of the GPL to prohibit the practice for those
|
||||
products. If such problems arise substantially in other domains, we
|
||||
stand ready to extend this provision to those domains in future versions
|
||||
of the GPL, as needed to protect the freedom of users.
|
||||
|
||||
Finally, every program is threatened constantly by software patents.
|
||||
States should not allow patents to restrict development and use of
|
||||
software on general-purpose computers, but in those that do, we wish to
|
||||
avoid the special danger that patents applied to a free program could
|
||||
make it effectively proprietary. To prevent this, the GPL assures that
|
||||
patents cannot be used to render the program non-free.
|
||||
|
||||
The precise terms and conditions for copying, distribution and
|
||||
modification follow.
|
||||
|
||||
TERMS AND CONDITIONS
|
||||
|
||||
0. Definitions.
|
||||
|
||||
"This License" refers to version 3 of the GNU General Public License.
|
||||
|
||||
"Copyright" also means copyright-like laws that apply to other kinds of
|
||||
works, such as semiconductor masks.
|
||||
|
||||
"The Program" refers to any copyrightable work licensed under this
|
||||
License. Each licensee is addressed as "you". "Licensees" and
|
||||
"recipients" may be individuals or organizations.
|
||||
|
||||
To "modify" a work means to copy from or adapt all or part of the work
|
||||
in a fashion requiring copyright permission, other than the making of an
|
||||
exact copy. The resulting work is called a "modified version" of the
|
||||
earlier work or a work "based on" the earlier work.
|
||||
|
||||
A "covered work" means either the unmodified Program or a work based
|
||||
on the Program.
|
||||
|
||||
To "propagate" a work means to do anything with it that, without
|
||||
permission, would make you directly or secondarily liable for
|
||||
infringement under applicable copyright law, except executing it on a
|
||||
computer or modifying a private copy. Propagation includes copying,
|
||||
distribution (with or without modification), making available to the
|
||||
public, and in some countries other activities as well.
|
||||
|
||||
To "convey" a work means any kind of propagation that enables other
|
||||
parties to make or receive copies. Mere interaction with a user through
|
||||
a computer network, with no transfer of a copy, is not conveying.
|
||||
|
||||
An interactive user interface displays "Appropriate Legal Notices"
|
||||
to the extent that it includes a convenient and prominently visible
|
||||
feature that (1) displays an appropriate copyright notice, and (2)
|
||||
tells the user that there is no warranty for the work (except to the
|
||||
extent that warranties are provided), that licensees may convey the
|
||||
work under this License, and how to view a copy of this License. If
|
||||
the interface presents a list of user commands or options, such as a
|
||||
menu, a prominent item in the list meets this criterion.
|
||||
|
||||
1. Source Code.
|
||||
|
||||
The "source code" for a work means the preferred form of the work
|
||||
for making modifications to it. "Object code" means any non-source
|
||||
form of a work.
|
||||
|
||||
A "Standard Interface" means an interface that either is an official
|
||||
standard defined by a recognized standards body, or, in the case of
|
||||
interfaces specified for a particular programming language, one that
|
||||
is widely used among developers working in that language.
|
||||
|
||||
The "System Libraries" of an executable work include anything, other
|
||||
than the work as a whole, that (a) is included in the normal form of
|
||||
packaging a Major Component, but which is not part of that Major
|
||||
Component, and (b) serves only to enable use of the work with that
|
||||
Major Component, or to implement a Standard Interface for which an
|
||||
implementation is available to the public in source code form. A
|
||||
"Major Component", in this context, means a major essential component
|
||||
(kernel, window system, and so on) of the specific operating system
|
||||
(if any) on which the executable work runs, or a compiler used to
|
||||
produce the work, or an object code interpreter used to run it.
|
||||
|
||||
The "Corresponding Source" for a work in object code form means all
|
||||
the source code needed to generate, install, and (for an executable
|
||||
work) run the object code and to modify the work, including scripts to
|
||||
control those activities. However, it does not include the work's
|
||||
System Libraries, or general-purpose tools or generally available free
|
||||
programs which are used unmodified in performing those activities but
|
||||
which are not part of the work. For example, Corresponding Source
|
||||
includes interface definition files associated with source files for
|
||||
the work, and the source code for shared libraries and dynamically
|
||||
linked subprograms that the work is specifically designed to require,
|
||||
such as by intimate data communication or control flow between those
|
||||
subprograms and other parts of the work.
|
||||
|
||||
The Corresponding Source need not include anything that users
|
||||
can regenerate automatically from other parts of the Corresponding
|
||||
Source.
|
||||
|
||||
The Corresponding Source for a work in source code form is that
|
||||
same work.
|
||||
|
||||
2. Basic Permissions.
|
||||
|
||||
All rights granted under this License are granted for the term of
|
||||
copyright on the Program, and are irrevocable provided the stated
|
||||
conditions are met. This License explicitly affirms your unlimited
|
||||
permission to run the unmodified Program. The output from running a
|
||||
covered work is covered by this License only if the output, given its
|
||||
content, constitutes a covered work. This License acknowledges your
|
||||
rights of fair use or other equivalent, as provided by copyright law.
|
||||
|
||||
You may make, run and propagate covered works that you do not
|
||||
convey, without conditions so long as your license otherwise remains
|
||||
in force. You may convey covered works to others for the sole purpose
|
||||
of having them make modifications exclusively for you, or provide you
|
||||
with facilities for running those works, provided that you comply with
|
||||
the terms of this License in conveying all material for which you do
|
||||
not control copyright. Those thus making or running the covered works
|
||||
for you must do so exclusively on your behalf, under your direction
|
||||
and control, on terms that prohibit them from making any copies of
|
||||
your copyrighted material outside their relationship with you.
|
||||
|
||||
Conveying under any other circumstances is permitted solely under
|
||||
the conditions stated below. Sublicensing is not allowed; section 10
|
||||
makes it unnecessary.
|
||||
|
||||
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
|
||||
|
||||
No covered work shall be deemed part of an effective technological
|
||||
measure under any applicable law fulfilling obligations under article
|
||||
11 of the WIPO copyright treaty adopted on 20 December 1996, or
|
||||
similar laws prohibiting or restricting circumvention of such
|
||||
measures.
|
||||
|
||||
When you convey a covered work, you waive any legal power to forbid
|
||||
circumvention of technological measures to the extent such circumvention
|
||||
is effected by exercising rights under this License with respect to
|
||||
the covered work, and you disclaim any intention to limit operation or
|
||||
modification of the work as a means of enforcing, against the work's
|
||||
users, your or third parties' legal rights to forbid circumvention of
|
||||
technological measures.
|
||||
|
||||
4. Conveying Verbatim Copies.
|
||||
|
||||
You may convey verbatim copies of the Program's source code as you
|
||||
receive it, in any medium, provided that you conspicuously and
|
||||
appropriately publish on each copy an appropriate copyright notice;
|
||||
keep intact all notices stating that this License and any
|
||||
non-permissive terms added in accord with section 7 apply to the code;
|
||||
keep intact all notices of the absence of any warranty; and give all
|
||||
recipients a copy of this License along with the Program.
|
||||
|
||||
You may charge any price or no price for each copy that you convey,
|
||||
and you may offer support or warranty protection for a fee.
|
||||
|
||||
5. Conveying Modified Source Versions.
|
||||
|
||||
You may convey a work based on the Program, or the modifications to
|
||||
produce it from the Program, in the form of source code under the
|
||||
terms of section 4, provided that you also meet all of these conditions:
|
||||
|
||||
a) The work must carry prominent notices stating that you modified
|
||||
it, and giving a relevant date.
|
||||
|
||||
b) The work must carry prominent notices stating that it is
|
||||
released under this License and any conditions added under section
|
||||
7. This requirement modifies the requirement in section 4 to
|
||||
"keep intact all notices".
|
||||
|
||||
c) You must license the entire work, as a whole, under this
|
||||
License to anyone who comes into possession of a copy. This
|
||||
License will therefore apply, along with any applicable section 7
|
||||
additional terms, to the whole of the work, and all its parts,
|
||||
regardless of how they are packaged. This License gives no
|
||||
permission to license the work in any other way, but it does not
|
||||
invalidate such permission if you have separately received it.
|
||||
|
||||
d) If the work has interactive user interfaces, each must display
|
||||
Appropriate Legal Notices; however, if the Program has interactive
|
||||
interfaces that do not display Appropriate Legal Notices, your
|
||||
work need not make them do so.
|
||||
|
||||
A compilation of a covered work with other separate and independent
|
||||
works, which are not by their nature extensions of the covered work,
|
||||
and which are not combined with it such as to form a larger program,
|
||||
in or on a volume of a storage or distribution medium, is called an
|
||||
"aggregate" if the compilation and its resulting copyright are not
|
||||
used to limit the access or legal rights of the compilation's users
|
||||
beyond what the individual works permit. Inclusion of a covered work
|
||||
in an aggregate does not cause this License to apply to the other
|
||||
parts of the aggregate.
|
||||
|
||||
6. Conveying Non-Source Forms.
|
||||
|
||||
You may convey a covered work in object code form under the terms
|
||||
of sections 4 and 5, provided that you also convey the
|
||||
machine-readable Corresponding Source under the terms of this License,
|
||||
in one of these ways:
|
||||
|
||||
a) Convey the object code in, or embodied in, a physical product
|
||||
(including a physical distribution medium), accompanied by the
|
||||
Corresponding Source fixed on a durable physical medium
|
||||
customarily used for software interchange.
|
||||
|
||||
b) Convey the object code in, or embodied in, a physical product
|
||||
(including a physical distribution medium), accompanied by a
|
||||
written offer, valid for at least three years and valid for as
|
||||
long as you offer spare parts or customer support for that product
|
||||
model, to give anyone who possesses the object code either (1) a
|
||||
copy of the Corresponding Source for all the software in the
|
||||
product that is covered by this License, on a durable physical
|
||||
medium customarily used for software interchange, for a price no
|
||||
more than your reasonable cost of physically performing this
|
||||
conveying of source, or (2) access to copy the
|
||||
Corresponding Source from a network server at no charge.
|
||||
|
||||
c) Convey individual copies of the object code with a copy of the
|
||||
written offer to provide the Corresponding Source. This
|
||||
alternative is allowed only occasionally and noncommercially, and
|
||||
only if you received the object code with such an offer, in accord
|
||||
with subsection 6b.
|
||||
|
||||
d) Convey the object code by offering access from a designated
|
||||
place (gratis or for a charge), and offer equivalent access to the
|
||||
Corresponding Source in the same way through the same place at no
|
||||
further charge. You need not require recipients to copy the
|
||||
Corresponding Source along with the object code. If the place to
|
||||
copy the object code is a network server, the Corresponding Source
|
||||
may be on a different server (operated by you or a third party)
|
||||
that supports equivalent copying facilities, provided you maintain
|
||||
clear directions next to the object code saying where to find the
|
||||
Corresponding Source. Regardless of what server hosts the
|
||||
Corresponding Source, you remain obligated to ensure that it is
|
||||
available for as long as needed to satisfy these requirements.
|
||||
|
||||
e) Convey the object code using peer-to-peer transmission, provided
|
||||
you inform other peers where the object code and Corresponding
|
||||
Source of the work are being offered to the general public at no
|
||||
charge under subsection 6d.
|
||||
|
||||
A separable portion of the object code, whose source code is excluded
|
||||
from the Corresponding Source as a System Library, need not be
|
||||
included in conveying the object code work.
|
||||
|
||||
A "User Product" is either (1) a "consumer product", which means any
|
||||
tangible personal property which is normally used for personal, family,
|
||||
or household purposes, or (2) anything designed or sold for incorporation
|
||||
into a dwelling. In determining whether a product is a consumer product,
|
||||
doubtful cases shall be resolved in favor of coverage. For a particular
|
||||
product received by a particular user, "normally used" refers to a
|
||||
typical or common use of that class of product, regardless of the status
|
||||
of the particular user or of the way in which the particular user
|
||||
actually uses, or expects or is expected to use, the product. A product
|
||||
is a consumer product regardless of whether the product has substantial
|
||||
commercial, industrial or non-consumer uses, unless such uses represent
|
||||
the only significant mode of use of the product.
|
||||
|
||||
"Installation Information" for a User Product means any methods,
|
||||
procedures, authorization keys, or other information required to install
|
||||
and execute modified versions of a covered work in that User Product from
|
||||
a modified version of its Corresponding Source. The information must
|
||||
suffice to ensure that the continued functioning of the modified object
|
||||
code is in no case prevented or interfered with solely because
|
||||
modification has been made.
|
||||
|
||||
If you convey an object code work under this section in, or with, or
|
||||
specifically for use in, a User Product, and the conveying occurs as
|
||||
part of a transaction in which the right of possession and use of the
|
||||
User Product is transferred to the recipient in perpetuity or for a
|
||||
fixed term (regardless of how the transaction is characterized), the
|
||||
Corresponding Source conveyed under this section must be accompanied
|
||||
by the Installation Information. But this requirement does not apply
|
||||
if neither you nor any third party retains the ability to install
|
||||
modified object code on the User Product (for example, the work has
|
||||
been installed in ROM).
|
||||
|
||||
The requirement to provide Installation Information does not include a
|
||||
requirement to continue to provide support service, warranty, or updates
|
||||
for a work that has been modified or installed by the recipient, or for
|
||||
the User Product in which it has been modified or installed. Access to a
|
||||
network may be denied when the modification itself materially and
|
||||
adversely affects the operation of the network or violates the rules and
|
||||
protocols for communication across the network.
|
||||
|
||||
Corresponding Source conveyed, and Installation Information provided,
|
||||
in accord with this section must be in a format that is publicly
|
||||
documented (and with an implementation available to the public in
|
||||
source code form), and must require no special password or key for
|
||||
unpacking, reading or copying.
|
||||
|
||||
7. Additional Terms.
|
||||
|
||||
"Additional permissions" are terms that supplement the terms of this
|
||||
License by making exceptions from one or more of its conditions.
|
||||
Additional permissions that are applicable to the entire Program shall
|
||||
be treated as though they were included in this License, to the extent
|
||||
that they are valid under applicable law. If additional permissions
|
||||
apply only to part of the Program, that part may be used separately
|
||||
under those permissions, but the entire Program remains governed by
|
||||
this License without regard to the additional permissions.
|
||||
|
||||
When you convey a copy of a covered work, you may at your option
|
||||
remove any additional permissions from that copy, or from any part of
|
||||
it. (Additional permissions may be written to require their own
|
||||
removal in certain cases when you modify the work.) You may place
|
||||
additional permissions on material, added by you to a covered work,
|
||||
for which you have or can give appropriate copyright permission.
|
||||
|
||||
Notwithstanding any other provision of this License, for material you
|
||||
add to a covered work, you may (if authorized by the copyright holders of
|
||||
that material) supplement the terms of this License with terms:
|
||||
|
||||
a) Disclaiming warranty or limiting liability differently from the
|
||||
terms of sections 15 and 16 of this License; or
|
||||
|
||||
b) Requiring preservation of specified reasonable legal notices or
|
||||
author attributions in that material or in the Appropriate Legal
|
||||
Notices displayed by works containing it; or
|
||||
|
||||
c) Prohibiting misrepresentation of the origin of that material, or
|
||||
requiring that modified versions of such material be marked in
|
||||
reasonable ways as different from the original version; or
|
||||
|
||||
d) Limiting the use for publicity purposes of names of licensors or
|
||||
authors of the material; or
|
||||
|
||||
e) Declining to grant rights under trademark law for use of some
|
||||
trade names, trademarks, or service marks; or
|
||||
|
||||
f) Requiring indemnification of licensors and authors of that
|
||||
material by anyone who conveys the material (or modified versions of
|
||||
it) with contractual assumptions of liability to the recipient, for
|
||||
any liability that these contractual assumptions directly impose on
|
||||
those licensors and authors.
|
||||
|
||||
All other non-permissive additional terms are considered "further
|
||||
restrictions" within the meaning of section 10. If the Program as you
|
||||
received it, or any part of it, contains a notice stating that it is
|
||||
governed by this License along with a term that is a further
|
||||
restriction, you may remove that term. If a license document contains
|
||||
a further restriction but permits relicensing or conveying under this
|
||||
License, you may add to a covered work material governed by the terms
|
||||
of that license document, provided that the further restriction does
|
||||
not survive such relicensing or conveying.
|
||||
|
||||
If you add terms to a covered work in accord with this section, you
|
||||
must place, in the relevant source files, a statement of the
|
||||
additional terms that apply to those files, or a notice indicating
|
||||
where to find the applicable terms.
|
||||
|
||||
Additional terms, permissive or non-permissive, may be stated in the
|
||||
form of a separately written license, or stated as exceptions;
|
||||
the above requirements apply either way.
|
||||
|
||||
8. Termination.
|
||||
|
||||
You may not propagate or modify a covered work except as expressly
|
||||
provided under this License. Any attempt otherwise to propagate or
|
||||
modify it is void, and will automatically terminate your rights under
|
||||
this License (including any patent licenses granted under the third
|
||||
paragraph of section 11).
|
||||
|
||||
However, if you cease all violation of this License, then your
|
||||
license from a particular copyright holder is reinstated (a)
|
||||
provisionally, unless and until the copyright holder explicitly and
|
||||
finally terminates your license, and (b) permanently, if the copyright
|
||||
holder fails to notify you of the violation by some reasonable means
|
||||
prior to 60 days after the cessation.
|
||||
|
||||
Moreover, your license from a particular copyright holder is
|
||||
reinstated permanently if the copyright holder notifies you of the
|
||||
violation by some reasonable means, this is the first time you have
|
||||
received notice of violation of this License (for any work) from that
|
||||
copyright holder, and you cure the violation prior to 30 days after
|
||||
your receipt of the notice.
|
||||
|
||||
Termination of your rights under this section does not terminate the
|
||||
licenses of parties who have received copies or rights from you under
|
||||
this License. If your rights have been terminated and not permanently
|
||||
reinstated, you do not qualify to receive new licenses for the same
|
||||
material under section 10.
|
||||
|
||||
9. Acceptance Not Required for Having Copies.
|
||||
|
||||
You are not required to accept this License in order to receive or
|
||||
run a copy of the Program. Ancillary propagation of a covered work
|
||||
occurring solely as a consequence of using peer-to-peer transmission
|
||||
to receive a copy likewise does not require acceptance. However,
|
||||
nothing other than this License grants you permission to propagate or
|
||||
modify any covered work. These actions infringe copyright if you do
|
||||
not accept this License. Therefore, by modifying or propagating a
|
||||
covered work, you indicate your acceptance of this License to do so.
|
||||
|
||||
10. Automatic Licensing of Downstream Recipients.
|
||||
|
||||
Each time you convey a covered work, the recipient automatically
|
||||
receives a license from the original licensors, to run, modify and
|
||||
propagate that work, subject to this License. You are not responsible
|
||||
for enforcing compliance by third parties with this License.
|
||||
|
||||
An "entity transaction" is a transaction transferring control of an
|
||||
organization, or substantially all assets of one, or subdividing an
|
||||
organization, or merging organizations. If propagation of a covered
|
||||
work results from an entity transaction, each party to that
|
||||
transaction who receives a copy of the work also receives whatever
|
||||
licenses to the work the party's predecessor in interest had or could
|
||||
give under the previous paragraph, plus a right to possession of the
|
||||
Corresponding Source of the work from the predecessor in interest, if
|
||||
the predecessor has it or can get it with reasonable efforts.
|
||||
|
||||
You may not impose any further restrictions on the exercise of the
|
||||
rights granted or affirmed under this License. For example, you may
|
||||
not impose a license fee, royalty, or other charge for exercise of
|
||||
rights granted under this License, and you may not initiate litigation
|
||||
(including a cross-claim or counterclaim in a lawsuit) alleging that
|
||||
any patent claim is infringed by making, using, selling, offering for
|
||||
sale, or importing the Program or any portion of it.
|
||||
|
||||
11. Patents.
|
||||
|
||||
A "contributor" is a copyright holder who authorizes use under this
|
||||
License of the Program or a work on which the Program is based. The
|
||||
work thus licensed is called the contributor's "contributor version".
|
||||
|
||||
A contributor's "essential patent claims" are all patent claims
|
||||
owned or controlled by the contributor, whether already acquired or
|
||||
hereafter acquired, that would be infringed by some manner, permitted
|
||||
by this License, of making, using, or selling its contributor version,
|
||||
but do not include claims that would be infringed only as a
|
||||
consequence of further modification of the contributor version. For
|
||||
purposes of this definition, "control" includes the right to grant
|
||||
patent sublicenses in a manner consistent with the requirements of
|
||||
this License.
|
||||
|
||||
Each contributor grants you a non-exclusive, worldwide, royalty-free
|
||||
patent license under the contributor's essential patent claims, to
|
||||
make, use, sell, offer for sale, import and otherwise run, modify and
|
||||
propagate the contents of its contributor version.
|
||||
|
||||
In the following three paragraphs, a "patent license" is any express
|
||||
agreement or commitment, however denominated, not to enforce a patent
|
||||
(such as an express permission to practice a patent or covenant not to
|
||||
sue for patent infringement). To "grant" such a patent license to a
|
||||
party means to make such an agreement or commitment not to enforce a
|
||||
patent against the party.
|
||||
|
||||
If you convey a covered work, knowingly relying on a patent license,
|
||||
and the Corresponding Source of the work is not available for anyone
|
||||
to copy, free of charge and under the terms of this License, through a
|
||||
publicly available network server or other readily accessible means,
|
||||
then you must either (1) cause the Corresponding Source to be so
|
||||
available, or (2) arrange to deprive yourself of the benefit of the
|
||||
patent license for this particular work, or (3) arrange, in a manner
|
||||
consistent with the requirements of this License, to extend the patent
|
||||
license to downstream recipients. "Knowingly relying" means you have
|
||||
actual knowledge that, but for the patent license, your conveying the
|
||||
covered work in a country, or your recipient's use of the covered work
|
||||
in a country, would infringe one or more identifiable patents in that
|
||||
country that you have reason to believe are valid.
|
||||
|
||||
If, pursuant to or in connection with a single transaction or
|
||||
arrangement, you convey, or propagate by procuring conveyance of, a
|
||||
covered work, and grant a patent license to some of the parties
|
||||
receiving the covered work authorizing them to use, propagate, modify
|
||||
or convey a specific copy of the covered work, then the patent license
|
||||
you grant is automatically extended to all recipients of the covered
|
||||
work and works based on it.
|
||||
|
||||
A patent license is "discriminatory" if it does not include within
|
||||
the scope of its coverage, prohibits the exercise of, or is
|
||||
conditioned on the non-exercise of one or more of the rights that are
|
||||
specifically granted under this License. You may not convey a covered
|
||||
work if you are a party to an arrangement with a third party that is
|
||||
in the business of distributing software, under which you make payment
|
||||
to the third party based on the extent of your activity of conveying
|
||||
the work, and under which the third party grants, to any of the
|
||||
parties who would receive the covered work from you, a discriminatory
|
||||
patent license (a) in connection with copies of the covered work
|
||||
conveyed by you (or copies made from those copies), or (b) primarily
|
||||
for and in connection with specific products or compilations that
|
||||
contain the covered work, unless you entered into that arrangement,
|
||||
or that patent license was granted, prior to 28 March 2007.
|
||||
|
||||
Nothing in this License shall be construed as excluding or limiting
|
||||
any implied license or other defenses to infringement that may
|
||||
otherwise be available to you under applicable patent law.
|
||||
|
||||
12. No Surrender of Others' Freedom.
|
||||
|
||||
If conditions are imposed on you (whether by court order, agreement or
|
||||
otherwise) that contradict the conditions of this License, they do not
|
||||
excuse you from the conditions of this License. If you cannot convey a
|
||||
covered work so as to satisfy simultaneously your obligations under this
|
||||
License and any other pertinent obligations, then as a consequence you may
|
||||
not convey it at all. For example, if you agree to terms that obligate you
|
||||
to collect a royalty for further conveying from those to whom you convey
|
||||
the Program, the only way you could satisfy both those terms and this
|
||||
License would be to refrain entirely from conveying the Program.
|
||||
|
||||
13. Use with the GNU Affero General Public License.
|
||||
|
||||
Notwithstanding any other provision of this License, you have
|
||||
permission to link or combine any covered work with a work licensed
|
||||
under version 3 of the GNU Affero General Public License into a single
|
||||
combined work, and to convey the resulting work. The terms of this
|
||||
License will continue to apply to the part which is the covered work,
|
||||
but the special requirements of the GNU Affero General Public License,
|
||||
section 13, concerning interaction through a network will apply to the
|
||||
combination as such.
|
||||
|
||||
14. Revised Versions of this License.
|
||||
|
||||
The Free Software Foundation may publish revised and/or new versions of
|
||||
the GNU General Public License from time to time. Such new versions will
|
||||
be similar in spirit to the present version, but may differ in detail to
|
||||
address new problems or concerns.
|
||||
|
||||
Each version is given a distinguishing version number. If the
|
||||
Program specifies that a certain numbered version of the GNU General
|
||||
Public License "or any later version" applies to it, you have the
|
||||
option of following the terms and conditions either of that numbered
|
||||
version or of any later version published by the Free Software
|
||||
Foundation. If the Program does not specify a version number of the
|
||||
GNU General Public License, you may choose any version ever published
|
||||
by the Free Software Foundation.
|
||||
|
||||
If the Program specifies that a proxy can decide which future
|
||||
versions of the GNU General Public License can be used, that proxy's
|
||||
public statement of acceptance of a version permanently authorizes you
|
||||
to choose that version for the Program.
|
||||
|
||||
Later license versions may give you additional or different
|
||||
permissions. However, no additional obligations are imposed on any
|
||||
author or copyright holder as a result of your choosing to follow a
|
||||
later version.
|
||||
|
||||
15. Disclaimer of Warranty.
|
||||
|
||||
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
|
||||
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
|
||||
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
|
||||
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
|
||||
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
||||
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
|
||||
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
|
||||
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
|
||||
|
||||
16. Limitation of Liability.
|
||||
|
||||
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
|
||||
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
|
||||
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
|
||||
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
|
||||
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
|
||||
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
|
||||
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
|
||||
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
|
||||
SUCH DAMAGES.
|
||||
|
||||
17. Interpretation of Sections 15 and 16.
|
||||
|
||||
If the disclaimer of warranty and limitation of liability provided
|
||||
above cannot be given local legal effect according to their terms,
|
||||
reviewing courts shall apply local law that most closely approximates
|
||||
an absolute waiver of all civil liability in connection with the
|
||||
Program, unless a warranty or assumption of liability accompanies a
|
||||
copy of the Program in return for a fee.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
How to Apply These Terms to Your New Programs
|
||||
|
||||
If you develop a new program, and you want it to be of the greatest
|
||||
possible use to the public, the best way to achieve this is to make it
|
||||
free software which everyone can redistribute and change under these terms.
|
||||
|
||||
To do so, attach the following notices to the program. It is safest
|
||||
to attach them to the start of each source file to most effectively
|
||||
state the exclusion of warranty; and each file should have at least
|
||||
the "copyright" line and a pointer to where the full notice is found.
|
||||
|
||||
<one line to give the program's name and a brief idea of what it does.>
|
||||
Copyright (C) <year> <name of author>
|
||||
|
||||
This program is free software: you can redistribute it and/or modify
|
||||
it under the terms of the GNU General Public License as published by
|
||||
the Free Software Foundation, either version 3 of the License, or
|
||||
(at your option) any later version.
|
||||
|
||||
This program is distributed in the hope that it will be useful,
|
||||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
GNU General Public License for more details.
|
||||
|
||||
You should have received a copy of the GNU General Public License
|
||||
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
Also add information on how to contact you by electronic and paper mail.
|
||||
|
||||
If the program does terminal interaction, make it output a short
|
||||
notice like this when it starts in an interactive mode:
|
||||
|
||||
<program> Copyright (C) <year> <name of author>
|
||||
This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
|
||||
This is free software, and you are welcome to redistribute it
|
||||
under certain conditions; type `show c' for details.
|
||||
|
||||
The hypothetical commands `show w' and `show c' should show the appropriate
|
||||
parts of the General Public License. Of course, your program's commands
|
||||
might be different; for a GUI interface, you would use an "about box".
|
||||
|
||||
You should also get your employer (if you work as a programmer) or school,
|
||||
if any, to sign a "copyright disclaimer" for the program, if necessary.
|
||||
For more information on this, and how to apply and follow the GNU GPL, see
|
||||
<http://www.gnu.org/licenses/>.
|
||||
|
||||
The GNU General Public License does not permit incorporating your program
|
||||
into proprietary programs. If your program is a subroutine library, you
|
||||
may consider it more useful to permit linking proprietary applications with
|
||||
the library. If this is what you want to do, use the GNU Lesser General
|
||||
Public License instead of this License. But first, please read
|
||||
<http://www.gnu.org/philosophy/why-not-lgpl.html>.
|
||||
@ -0,0 +1,10 @@
|
||||
DEEPSORT:
|
||||
REID_CKPT: "deep_sort/deep_sort/deep/checkpoint/ckpt.t7"
|
||||
MAX_DIST: 0.2
|
||||
MIN_CONFIDENCE: 0.3
|
||||
NMS_MAX_OVERLAP: 0.5
|
||||
MAX_IOU_DISTANCE: 0.7
|
||||
MAX_AGE: 70
|
||||
N_INIT: 3
|
||||
NN_BUDGET: 100
|
||||
|
||||
@ -0,0 +1,3 @@
|
||||
# Deep Sort
|
||||
|
||||
This is the implemention of deep sort with pytorch.
|
||||
@ -0,0 +1,21 @@
|
||||
from .deep_sort import DeepSort
|
||||
|
||||
|
||||
__all__ = ['DeepSort', 'build_tracker']
|
||||
|
||||
|
||||
def build_tracker(cfg, use_cuda):
|
||||
return DeepSort(cfg.DEEPSORT.REID_CKPT,
|
||||
max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
|
||||
nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
|
||||
max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET, use_cuda=use_cuda)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
Binary file not shown.
@ -0,0 +1,15 @@
|
||||
import torch
|
||||
|
||||
features = torch.load("features.pth")
|
||||
qf = features["qf"]
|
||||
ql = features["ql"]
|
||||
gf = features["gf"]
|
||||
gl = features["gl"]
|
||||
|
||||
scores = qf.mm(gf.t())
|
||||
res = scores.topk(5, dim=1)[1][:,0]
|
||||
top1correct = gl[res].eq(ql).sum().item()
|
||||
|
||||
print("Acc top1:{:.3f}".format(top1correct/ql.size(0)))
|
||||
|
||||
|
||||
@ -0,0 +1,55 @@
|
||||
import torch
|
||||
import torchvision.transforms as transforms
|
||||
import numpy as np
|
||||
import cv2
|
||||
import logging
|
||||
|
||||
from .model import Net
|
||||
|
||||
class Extractor(object):
|
||||
def __init__(self, model_path, use_cuda=True):
|
||||
self.net = Net(reid=True)
|
||||
self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
|
||||
state_dict = torch.load(model_path, map_location=lambda storage, loc: storage)['net_dict']
|
||||
self.net.load_state_dict(state_dict)
|
||||
logger = logging.getLogger("root.tracker")
|
||||
logger.info("Loading weights from {}... Done!".format(model_path))
|
||||
self.net.to(self.device)
|
||||
self.size = (64, 128)
|
||||
self.norm = transforms.Compose([
|
||||
transforms.ToTensor(),
|
||||
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
|
||||
])
|
||||
|
||||
|
||||
|
||||
def _preprocess(self, im_crops):
|
||||
"""
|
||||
TODO:
|
||||
1. to float with scale from 0 to 1
|
||||
2. resize to (64, 128) as Market1501 dataset did
|
||||
3. concatenate to a numpy array
|
||||
3. to torch Tensor
|
||||
4. normalize
|
||||
"""
|
||||
def _resize(im, size):
|
||||
return cv2.resize(im.astype(np.float32)/255., size)
|
||||
|
||||
im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(0) for im in im_crops], dim=0).float()
|
||||
return im_batch
|
||||
|
||||
|
||||
def __call__(self, im_crops):
|
||||
im_batch = self._preprocess(im_crops)
|
||||
with torch.no_grad():
|
||||
im_batch = im_batch.to(self.device)
|
||||
features = self.net(im_batch)
|
||||
return features.cpu().numpy()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
img = cv2.imread("demo.jpg")[:,:,(2,1,0)]
|
||||
extr = Extractor("checkpoint/ckpt.t7")
|
||||
feature = extr(img)
|
||||
print(feature.shape)
|
||||
|
||||
@ -0,0 +1,104 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
class BasicBlock(nn.Module):
|
||||
def __init__(self, c_in, c_out,is_downsample=False):
|
||||
super(BasicBlock,self).__init__()
|
||||
self.is_downsample = is_downsample
|
||||
if is_downsample:
|
||||
self.conv1 = nn.Conv2d(c_in, c_out, 3, stride=2, padding=1, bias=False)
|
||||
else:
|
||||
self.conv1 = nn.Conv2d(c_in, c_out, 3, stride=1, padding=1, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(c_out)
|
||||
self.relu = nn.ReLU(True)
|
||||
self.conv2 = nn.Conv2d(c_out,c_out,3,stride=1,padding=1, bias=False)
|
||||
self.bn2 = nn.BatchNorm2d(c_out)
|
||||
if is_downsample:
|
||||
self.downsample = nn.Sequential(
|
||||
nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
|
||||
nn.BatchNorm2d(c_out)
|
||||
)
|
||||
elif c_in != c_out:
|
||||
self.downsample = nn.Sequential(
|
||||
nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(c_out)
|
||||
)
|
||||
self.is_downsample = True
|
||||
|
||||
def forward(self,x):
|
||||
y = self.conv1(x)
|
||||
y = self.bn1(y)
|
||||
y = self.relu(y)
|
||||
y = self.conv2(y)
|
||||
y = self.bn2(y)
|
||||
if self.is_downsample:
|
||||
x = self.downsample(x)
|
||||
return F.relu(x.add(y),True)
|
||||
|
||||
def make_layers(c_in,c_out,repeat_times, is_downsample=False):
|
||||
blocks = []
|
||||
for i in range(repeat_times):
|
||||
if i ==0:
|
||||
blocks += [BasicBlock(c_in,c_out, is_downsample=is_downsample),]
|
||||
else:
|
||||
blocks += [BasicBlock(c_out,c_out),]
|
||||
return nn.Sequential(*blocks)
|
||||
|
||||
class Net(nn.Module):
|
||||
def __init__(self, num_classes=751 ,reid=False):
|
||||
super(Net,self).__init__()
|
||||
# 3 128 64
|
||||
self.conv = nn.Sequential(
|
||||
nn.Conv2d(3,64,3,stride=1,padding=1),
|
||||
nn.BatchNorm2d(64),
|
||||
nn.ReLU(inplace=True),
|
||||
# nn.Conv2d(32,32,3,stride=1,padding=1),
|
||||
# nn.BatchNorm2d(32),
|
||||
# nn.ReLU(inplace=True),
|
||||
nn.MaxPool2d(3,2,padding=1),
|
||||
)
|
||||
# 32 64 32
|
||||
self.layer1 = make_layers(64,64,2,False)
|
||||
# 32 64 32
|
||||
self.layer2 = make_layers(64,128,2,True)
|
||||
# 64 32 16
|
||||
self.layer3 = make_layers(128,256,2,True)
|
||||
# 128 16 8
|
||||
self.layer4 = make_layers(256,512,2,True)
|
||||
# 256 8 4
|
||||
self.avgpool = nn.AvgPool2d((8,4),1)
|
||||
# 256 1 1
|
||||
self.reid = reid
|
||||
self.classifier = nn.Sequential(
|
||||
nn.Linear(512, 256),
|
||||
nn.BatchNorm1d(256),
|
||||
nn.ReLU(inplace=True),
|
||||
nn.Dropout(),
|
||||
nn.Linear(256, num_classes),
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv(x)
|
||||
x = self.layer1(x)
|
||||
x = self.layer2(x)
|
||||
x = self.layer3(x)
|
||||
x = self.layer4(x)
|
||||
x = self.avgpool(x)
|
||||
x = x.view(x.size(0),-1)
|
||||
# B x 128
|
||||
if self.reid:
|
||||
x = x.div(x.norm(p=2,dim=1,keepdim=True))
|
||||
return x
|
||||
# classifier
|
||||
x = self.classifier(x)
|
||||
return x
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
net = Net()
|
||||
x = torch.randn(4,3,128,64)
|
||||
y = net(x)
|
||||
import ipdb; ipdb.set_trace()
|
||||
|
||||
|
||||
@ -0,0 +1,106 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
class BasicBlock(nn.Module):
|
||||
def __init__(self, c_in, c_out,is_downsample=False):
|
||||
super(BasicBlock,self).__init__()
|
||||
self.is_downsample = is_downsample
|
||||
if is_downsample:
|
||||
self.conv1 = nn.Conv2d(c_in, c_out, 3, stride=2, padding=1, bias=False)
|
||||
else:
|
||||
self.conv1 = nn.Conv2d(c_in, c_out, 3, stride=1, padding=1, bias=False)
|
||||
self.bn1 = nn.BatchNorm2d(c_out)
|
||||
self.relu = nn.ReLU(True)
|
||||
self.conv2 = nn.Conv2d(c_out,c_out,3,stride=1,padding=1, bias=False)
|
||||
self.bn2 = nn.BatchNorm2d(c_out)
|
||||
if is_downsample:
|
||||
self.downsample = nn.Sequential(
|
||||
nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
|
||||
nn.BatchNorm2d(c_out)
|
||||
)
|
||||
elif c_in != c_out:
|
||||
self.downsample = nn.Sequential(
|
||||
nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
|
||||
nn.BatchNorm2d(c_out)
|
||||
)
|
||||
self.is_downsample = True
|
||||
|
||||
def forward(self,x):
|
||||
y = self.conv1(x)
|
||||
y = self.bn1(y)
|
||||
y = self.relu(y)
|
||||
y = self.conv2(y)
|
||||
y = self.bn2(y)
|
||||
if self.is_downsample:
|
||||
x = self.downsample(x)
|
||||
return F.relu(x.add(y),True)
|
||||
|
||||
def make_layers(c_in,c_out,repeat_times, is_downsample=False):
|
||||
blocks = []
|
||||
for i in range(repeat_times):
|
||||
if i ==0:
|
||||
blocks += [BasicBlock(c_in,c_out, is_downsample=is_downsample),]
|
||||
else:
|
||||
blocks += [BasicBlock(c_out,c_out),]
|
||||
return nn.Sequential(*blocks)
|
||||
|
||||
class Net(nn.Module):
|
||||
def __init__(self, num_classes=625 ,reid=False):
|
||||
super(Net,self).__init__()
|
||||
# 3 128 64
|
||||
self.conv = nn.Sequential(
|
||||
nn.Conv2d(3,32,3,stride=1,padding=1),
|
||||
nn.BatchNorm2d(32),
|
||||
nn.ELU(inplace=True),
|
||||
nn.Conv2d(32,32,3,stride=1,padding=1),
|
||||
nn.BatchNorm2d(32),
|
||||
nn.ELU(inplace=True),
|
||||
nn.MaxPool2d(3,2,padding=1),
|
||||
)
|
||||
# 32 64 32
|
||||
self.layer1 = make_layers(32,32,2,False)
|
||||
# 32 64 32
|
||||
self.layer2 = make_layers(32,64,2,True)
|
||||
# 64 32 16
|
||||
self.layer3 = make_layers(64,128,2,True)
|
||||
# 128 16 8
|
||||
self.dense = nn.Sequential(
|
||||
nn.Dropout(p=0.6),
|
||||
nn.Linear(128*16*8, 128),
|
||||
nn.BatchNorm1d(128),
|
||||
nn.ELU(inplace=True)
|
||||
)
|
||||
# 256 1 1
|
||||
self.reid = reid
|
||||
self.batch_norm = nn.BatchNorm1d(128)
|
||||
self.classifier = nn.Sequential(
|
||||
nn.Linear(128, num_classes),
|
||||
)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.conv(x)
|
||||
x = self.layer1(x)
|
||||
x = self.layer2(x)
|
||||
x = self.layer3(x)
|
||||
|
||||
x = x.view(x.size(0),-1)
|
||||
if self.reid:
|
||||
x = self.dense[0](x)
|
||||
x = self.dense[1](x)
|
||||
x = x.div(x.norm(p=2,dim=1,keepdim=True))
|
||||
return x
|
||||
x = self.dense(x)
|
||||
# B x 128
|
||||
# classifier
|
||||
x = self.classifier(x)
|
||||
return x
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
net = Net(reid=True)
|
||||
x = torch.randn(4,3,128,64)
|
||||
y = net(x)
|
||||
import ipdb; ipdb.set_trace()
|
||||
|
||||
|
||||
@ -0,0 +1,77 @@
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
import torchvision
|
||||
|
||||
import argparse
|
||||
import os
|
||||
|
||||
from model import Net
|
||||
|
||||
parser = argparse.ArgumentParser(description="Train on market1501")
|
||||
parser.add_argument("--data-dir",default='data',type=str)
|
||||
parser.add_argument("--no-cuda",action="store_true")
|
||||
parser.add_argument("--gpu-id",default=0,type=int)
|
||||
args = parser.parse_args()
|
||||
|
||||
# device
|
||||
device = "cuda:{}".format(args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
|
||||
if torch.cuda.is_available() and not args.no_cuda:
|
||||
cudnn.benchmark = True
|
||||
|
||||
# data loader
|
||||
root = args.data_dir
|
||||
query_dir = os.path.join(root,"query")
|
||||
gallery_dir = os.path.join(root,"gallery")
|
||||
transform = torchvision.transforms.Compose([
|
||||
torchvision.transforms.Resize((128,64)),
|
||||
torchvision.transforms.ToTensor(),
|
||||
torchvision.transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
|
||||
])
|
||||
queryloader = torch.utils.data.DataLoader(
|
||||
torchvision.datasets.ImageFolder(query_dir, transform=transform),
|
||||
batch_size=64, shuffle=False
|
||||
)
|
||||
galleryloader = torch.utils.data.DataLoader(
|
||||
torchvision.datasets.ImageFolder(gallery_dir, transform=transform),
|
||||
batch_size=64, shuffle=False
|
||||
)
|
||||
|
||||
# net definition
|
||||
net = Net(reid=True)
|
||||
assert os.path.isfile("./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
|
||||
print('Loading from checkpoint/ckpt.t7')
|
||||
checkpoint = torch.load("./checkpoint/ckpt.t7")
|
||||
net_dict = checkpoint['net_dict']
|
||||
net.load_state_dict(net_dict, strict=False)
|
||||
net.eval()
|
||||
net.to(device)
|
||||
|
||||
# compute features
|
||||
query_features = torch.tensor([]).float()
|
||||
query_labels = torch.tensor([]).long()
|
||||
gallery_features = torch.tensor([]).float()
|
||||
gallery_labels = torch.tensor([]).long()
|
||||
|
||||
with torch.no_grad():
|
||||
for idx,(inputs,labels) in enumerate(queryloader):
|
||||
inputs = inputs.to(device)
|
||||
features = net(inputs).cpu()
|
||||
query_features = torch.cat((query_features, features), dim=0)
|
||||
query_labels = torch.cat((query_labels, labels))
|
||||
|
||||
for idx,(inputs,labels) in enumerate(galleryloader):
|
||||
inputs = inputs.to(device)
|
||||
features = net(inputs).cpu()
|
||||
gallery_features = torch.cat((gallery_features, features), dim=0)
|
||||
gallery_labels = torch.cat((gallery_labels, labels))
|
||||
|
||||
gallery_labels -= 2
|
||||
|
||||
# save features
|
||||
features = {
|
||||
"qf": query_features,
|
||||
"ql": query_labels,
|
||||
"gf": gallery_features,
|
||||
"gl": gallery_labels
|
||||
}
|
||||
torch.save(features,"features.pth")
|
||||
|
After Width: | Height: | Size: 59 KiB |
@ -0,0 +1,189 @@
|
||||
import argparse
|
||||
import os
|
||||
import time
|
||||
|
||||
import numpy as np
|
||||
import matplotlib.pyplot as plt
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
import torchvision
|
||||
|
||||
from model import Net
|
||||
|
||||
parser = argparse.ArgumentParser(description="Train on market1501")
|
||||
parser.add_argument("--data-dir",default='data',type=str)
|
||||
parser.add_argument("--no-cuda",action="store_true")
|
||||
parser.add_argument("--gpu-id",default=0,type=int)
|
||||
parser.add_argument("--lr",default=0.1, type=float)
|
||||
parser.add_argument("--interval",'-i',default=20,type=int)
|
||||
parser.add_argument('--resume', '-r',action='store_true')
|
||||
args = parser.parse_args()
|
||||
|
||||
# device
|
||||
device = "cuda:{}".format(args.gpu_id) if torch.cuda.is_available() and not args.no_cuda else "cpu"
|
||||
if torch.cuda.is_available() and not args.no_cuda:
|
||||
cudnn.benchmark = True
|
||||
|
||||
# data loading
|
||||
root = args.data_dir
|
||||
train_dir = os.path.join(root,"train")
|
||||
test_dir = os.path.join(root,"test")
|
||||
transform_train = torchvision.transforms.Compose([
|
||||
torchvision.transforms.RandomCrop((128,64),padding=4),
|
||||
torchvision.transforms.RandomHorizontalFlip(),
|
||||
torchvision.transforms.ToTensor(),
|
||||
torchvision.transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
|
||||
])
|
||||
transform_test = torchvision.transforms.Compose([
|
||||
torchvision.transforms.Resize((128,64)),
|
||||
torchvision.transforms.ToTensor(),
|
||||
torchvision.transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
|
||||
])
|
||||
trainloader = torch.utils.data.DataLoader(
|
||||
torchvision.datasets.ImageFolder(train_dir, transform=transform_train),
|
||||
batch_size=64,shuffle=True
|
||||
)
|
||||
testloader = torch.utils.data.DataLoader(
|
||||
torchvision.datasets.ImageFolder(test_dir, transform=transform_test),
|
||||
batch_size=64,shuffle=True
|
||||
)
|
||||
num_classes = max(len(trainloader.dataset.classes), len(testloader.dataset.classes))
|
||||
|
||||
# net definition
|
||||
start_epoch = 0
|
||||
net = Net(num_classes=num_classes)
|
||||
if args.resume:
|
||||
assert os.path.isfile("./checkpoint/ckpt.t7"), "Error: no checkpoint file found!"
|
||||
print('Loading from checkpoint/ckpt.t7')
|
||||
checkpoint = torch.load("./checkpoint/ckpt.t7")
|
||||
# import ipdb; ipdb.set_trace()
|
||||
net_dict = checkpoint['net_dict']
|
||||
net.load_state_dict(net_dict)
|
||||
best_acc = checkpoint['acc']
|
||||
start_epoch = checkpoint['epoch']
|
||||
net.to(device)
|
||||
|
||||
# loss and optimizer
|
||||
criterion = torch.nn.CrossEntropyLoss()
|
||||
optimizer = torch.optim.SGD(net.parameters(), args.lr, momentum=0.9, weight_decay=5e-4)
|
||||
best_acc = 0.
|
||||
|
||||
# train function for each epoch
|
||||
def train(epoch):
|
||||
print("\nEpoch : %d"%(epoch+1))
|
||||
net.train()
|
||||
training_loss = 0.
|
||||
train_loss = 0.
|
||||
correct = 0
|
||||
total = 0
|
||||
interval = args.interval
|
||||
start = time.time()
|
||||
for idx, (inputs, labels) in enumerate(trainloader):
|
||||
# forward
|
||||
inputs,labels = inputs.to(device),labels.to(device)
|
||||
outputs = net(inputs)
|
||||
loss = criterion(outputs, labels)
|
||||
|
||||
# backward
|
||||
optimizer.zero_grad()
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
# accumurating
|
||||
training_loss += loss.item()
|
||||
train_loss += loss.item()
|
||||
correct += outputs.max(dim=1)[1].eq(labels).sum().item()
|
||||
total += labels.size(0)
|
||||
|
||||
# print
|
||||
if (idx+1)%interval == 0:
|
||||
end = time.time()
|
||||
print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
|
||||
100.*(idx+1)/len(trainloader), end-start, training_loss/interval, correct, total, 100.*correct/total
|
||||
))
|
||||
training_loss = 0.
|
||||
start = time.time()
|
||||
|
||||
return train_loss/len(trainloader), 1.- correct/total
|
||||
|
||||
def test(epoch):
|
||||
global best_acc
|
||||
net.eval()
|
||||
test_loss = 0.
|
||||
correct = 0
|
||||
total = 0
|
||||
start = time.time()
|
||||
with torch.no_grad():
|
||||
for idx, (inputs, labels) in enumerate(testloader):
|
||||
inputs, labels = inputs.to(device), labels.to(device)
|
||||
outputs = net(inputs)
|
||||
loss = criterion(outputs, labels)
|
||||
|
||||
test_loss += loss.item()
|
||||
correct += outputs.max(dim=1)[1].eq(labels).sum().item()
|
||||
total += labels.size(0)
|
||||
|
||||
print("Testing ...")
|
||||
end = time.time()
|
||||
print("[progress:{:.1f}%]time:{:.2f}s Loss:{:.5f} Correct:{}/{} Acc:{:.3f}%".format(
|
||||
100.*(idx+1)/len(testloader), end-start, test_loss/len(testloader), correct, total, 100.*correct/total
|
||||
))
|
||||
|
||||
# saving checkpoint
|
||||
acc = 100.*correct/total
|
||||
if acc > best_acc:
|
||||
best_acc = acc
|
||||
print("Saving parameters to checkpoint/ckpt.t7")
|
||||
checkpoint = {
|
||||
'net_dict':net.state_dict(),
|
||||
'acc':acc,
|
||||
'epoch':epoch,
|
||||
}
|
||||
if not os.path.isdir('checkpoint'):
|
||||
os.mkdir('checkpoint')
|
||||
torch.save(checkpoint, './checkpoint/ckpt.t7')
|
||||
|
||||
return test_loss/len(testloader), 1.- correct/total
|
||||
|
||||
# plot figure
|
||||
x_epoch = []
|
||||
record = {'train_loss':[], 'train_err':[], 'test_loss':[], 'test_err':[]}
|
||||
fig = plt.figure()
|
||||
ax0 = fig.add_subplot(121, title="loss")
|
||||
ax1 = fig.add_subplot(122, title="top1err")
|
||||
def draw_curve(epoch, train_loss, train_err, test_loss, test_err):
|
||||
global record
|
||||
record['train_loss'].append(train_loss)
|
||||
record['train_err'].append(train_err)
|
||||
record['test_loss'].append(test_loss)
|
||||
record['test_err'].append(test_err)
|
||||
|
||||
x_epoch.append(epoch)
|
||||
ax0.plot(x_epoch, record['train_loss'], 'bo-', label='train')
|
||||
ax0.plot(x_epoch, record['test_loss'], 'ro-', label='val')
|
||||
ax1.plot(x_epoch, record['train_err'], 'bo-', label='train')
|
||||
ax1.plot(x_epoch, record['test_err'], 'ro-', label='val')
|
||||
if epoch == 0:
|
||||
ax0.legend()
|
||||
ax1.legend()
|
||||
fig.savefig("train.jpg")
|
||||
|
||||
# lr decay
|
||||
def lr_decay():
|
||||
global optimizer
|
||||
for params in optimizer.param_groups:
|
||||
params['lr'] *= 0.1
|
||||
lr = params['lr']
|
||||
print("Learning rate adjusted to {}".format(lr))
|
||||
|
||||
def main():
|
||||
for epoch in range(start_epoch, start_epoch+40):
|
||||
train_loss, train_err = train(epoch)
|
||||
test_loss, test_err = test(epoch)
|
||||
draw_curve(epoch, train_loss, train_err, test_loss, test_err)
|
||||
if (epoch+1)%20==0:
|
||||
lr_decay()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@ -0,0 +1,100 @@
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from .deep.feature_extractor import Extractor
|
||||
from .sort.nn_matching import NearestNeighborDistanceMetric
|
||||
from .sort.preprocessing import non_max_suppression
|
||||
from .sort.detection import Detection
|
||||
from .sort.tracker import Tracker
|
||||
|
||||
|
||||
__all__ = ['DeepSort']
|
||||
|
||||
|
||||
class DeepSort(object):
|
||||
def __init__(self, model_path, max_dist=0.2, min_confidence=0.3, nms_max_overlap=1.0, max_iou_distance=0.7, max_age=70, n_init=3, nn_budget=100, use_cuda=True):
|
||||
self.min_confidence = min_confidence
|
||||
self.nms_max_overlap = nms_max_overlap
|
||||
|
||||
self.extractor = Extractor(model_path, use_cuda=use_cuda)
|
||||
|
||||
max_cosine_distance = max_dist
|
||||
nn_budget = 100
|
||||
metric = NearestNeighborDistanceMetric(
|
||||
"cosine", max_cosine_distance, nn_budget)
|
||||
self.tracker = Tracker(
|
||||
metric, max_iou_distance=max_iou_distance, max_age=max_age, n_init=n_init)
|
||||
|
||||
def update(self, bbox_xywh, confidences, clss, ori_img):
|
||||
self.height, self.width = ori_img.shape[:2]
|
||||
# generate detections
|
||||
features = self._get_features(bbox_xywh, ori_img)
|
||||
bbox_tlwh = self._xywh_to_tlwh(bbox_xywh)
|
||||
detections = [Detection(bbox_tlwh[i], clss[i], conf, features[i]) for i, conf in enumerate(
|
||||
confidences) if conf > self.min_confidence]
|
||||
# update tracker
|
||||
self.tracker.predict()
|
||||
self.tracker.update(detections)
|
||||
|
||||
# output bbox identities
|
||||
outputs = []
|
||||
for track in self.tracker.tracks:
|
||||
if not track.is_confirmed() or track.time_since_update > 1:
|
||||
continue
|
||||
box = track.to_tlwh()
|
||||
x1, y1, x2, y2 = self._tlwh_to_xyxy(box)
|
||||
outputs.append((x1, y1, x2, y2, track.cls_, track.track_id))
|
||||
return outputs
|
||||
|
||||
@staticmethod
|
||||
def _xywh_to_tlwh(bbox_xywh):
|
||||
if isinstance(bbox_xywh, np.ndarray):
|
||||
bbox_tlwh = bbox_xywh.copy()
|
||||
elif isinstance(bbox_xywh, torch.Tensor):
|
||||
bbox_tlwh = bbox_xywh.clone()
|
||||
if bbox_tlwh.size(0):
|
||||
bbox_tlwh[:, 0] = bbox_xywh[:, 0] - bbox_xywh[:, 2]/2.
|
||||
bbox_tlwh[:, 1] = bbox_xywh[:, 1] - bbox_xywh[:, 3]/2.
|
||||
return bbox_tlwh
|
||||
|
||||
def _xywh_to_xyxy(self, bbox_xywh):
|
||||
x, y, w, h = bbox_xywh
|
||||
x1 = max(int(x-w/2), 0)
|
||||
x2 = min(int(x+w/2), self.width-1)
|
||||
y1 = max(int(y-h/2), 0)
|
||||
y2 = min(int(y+h/2), self.height-1)
|
||||
return x1, y1, x2, y2
|
||||
|
||||
def _tlwh_to_xyxy(self, bbox_tlwh):
|
||||
"""
|
||||
TODO:
|
||||
Convert bbox from xtl_ytl_w_h to xc_yc_w_h
|
||||
Thanks JieChen91@github.com for reporting this bug!
|
||||
"""
|
||||
x, y, w, h = bbox_tlwh
|
||||
x1 = max(int(x), 0)
|
||||
x2 = min(int(x+w), self.width-1)
|
||||
y1 = max(int(y), 0)
|
||||
y2 = min(int(y+h), self.height-1)
|
||||
return x1, y1, x2, y2
|
||||
|
||||
def _xyxy_to_tlwh(self, bbox_xyxy):
|
||||
x1, y1, x2, y2 = bbox_xyxy
|
||||
|
||||
t = x1
|
||||
l = y1
|
||||
w = int(x2-x1)
|
||||
h = int(y2-y1)
|
||||
return t, l, w, h
|
||||
|
||||
def _get_features(self, bbox_xywh, ori_img):
|
||||
im_crops = []
|
||||
for box in bbox_xywh:
|
||||
x1, y1, x2, y2 = self._xywh_to_xyxy(box)
|
||||
im = ori_img[y1:y2, x1:x2]
|
||||
im_crops.append(im)
|
||||
if im_crops:
|
||||
features = self.extractor(im_crops)
|
||||
else:
|
||||
features = np.array([])
|
||||
return features
|
||||
@ -0,0 +1,28 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
import numpy as np
|
||||
|
||||
|
||||
class Detection(object):
|
||||
|
||||
def __init__(self, tlwh, cls_, confidence, feature):
|
||||
self.tlwh = np.asarray(tlwh, dtype=np.float32)
|
||||
self.cls_ = cls_
|
||||
self.confidence = float(confidence)
|
||||
self.feature = np.asarray(feature, dtype=np.float32)
|
||||
|
||||
def to_tlbr(self):
|
||||
"""Convert bounding box to format `(min x, min y, max x, max y)`, i.e.,
|
||||
`(top left, bottom right)`.
|
||||
"""
|
||||
ret = self.tlwh.copy()
|
||||
ret[2:] += ret[:2]
|
||||
return ret
|
||||
|
||||
def to_xyah(self):
|
||||
"""Convert bounding box to format `(center x, center y, aspect ratio,
|
||||
height)`, where the aspect ratio is `width / height`.
|
||||
"""
|
||||
ret = self.tlwh.copy()
|
||||
ret[:2] += ret[2:] / 2
|
||||
ret[2] /= ret[3]
|
||||
return ret
|
||||
@ -0,0 +1,81 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
from __future__ import absolute_import
|
||||
import numpy as np
|
||||
from . import linear_assignment
|
||||
|
||||
|
||||
def iou(bbox, candidates):
|
||||
"""Computer intersection over union.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
bbox : ndarray
|
||||
A bounding box in format `(top left x, top left y, width, height)`.
|
||||
candidates : ndarray
|
||||
A matrix of candidate bounding boxes (one per row) in the same format
|
||||
as `bbox`.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
The intersection over union in [0, 1] between the `bbox` and each
|
||||
candidate. A higher score means a larger fraction of the `bbox` is
|
||||
occluded by the candidate.
|
||||
|
||||
"""
|
||||
bbox_tl, bbox_br = bbox[:2], bbox[:2] + bbox[2:]
|
||||
candidates_tl = candidates[:, :2]
|
||||
candidates_br = candidates[:, :2] + candidates[:, 2:]
|
||||
|
||||
tl = np.c_[np.maximum(bbox_tl[0], candidates_tl[:, 0])[:, np.newaxis],
|
||||
np.maximum(bbox_tl[1], candidates_tl[:, 1])[:, np.newaxis]]
|
||||
br = np.c_[np.minimum(bbox_br[0], candidates_br[:, 0])[:, np.newaxis],
|
||||
np.minimum(bbox_br[1], candidates_br[:, 1])[:, np.newaxis]]
|
||||
wh = np.maximum(0., br - tl)
|
||||
|
||||
area_intersection = wh.prod(axis=1)
|
||||
area_bbox = bbox[2:].prod()
|
||||
area_candidates = candidates[:, 2:].prod(axis=1)
|
||||
return area_intersection / (area_bbox + area_candidates - area_intersection)
|
||||
|
||||
|
||||
def iou_cost(tracks, detections, track_indices=None,
|
||||
detection_indices=None):
|
||||
"""An intersection over union distance metric.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
tracks : List[deep_sort.track.Track]
|
||||
A list of tracks.
|
||||
detections : List[deep_sort.detection.Detection]
|
||||
A list of detections.
|
||||
track_indices : Optional[List[int]]
|
||||
A list of indices to tracks that should be matched. Defaults to
|
||||
all `tracks`.
|
||||
detection_indices : Optional[List[int]]
|
||||
A list of indices to detections that should be matched. Defaults
|
||||
to all `detections`.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
Returns a cost matrix of shape
|
||||
len(track_indices), len(detection_indices) where entry (i, j) is
|
||||
`1 - iou(tracks[track_indices[i]], detections[detection_indices[j]])`.
|
||||
|
||||
"""
|
||||
if track_indices is None:
|
||||
track_indices = np.arange(len(tracks))
|
||||
if detection_indices is None:
|
||||
detection_indices = np.arange(len(detections))
|
||||
|
||||
cost_matrix = np.zeros((len(track_indices), len(detection_indices)))
|
||||
for row, track_idx in enumerate(track_indices):
|
||||
if tracks[track_idx].time_since_update > 1:
|
||||
cost_matrix[row, :] = linear_assignment.INFTY_COST
|
||||
continue
|
||||
|
||||
bbox = tracks[track_idx].to_tlwh()
|
||||
candidates = np.asarray([detections[i].tlwh for i in detection_indices])
|
||||
cost_matrix[row, :] = 1. - iou(bbox, candidates)
|
||||
return cost_matrix
|
||||
@ -0,0 +1,229 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
import numpy as np
|
||||
import scipy.linalg
|
||||
|
||||
|
||||
"""
|
||||
Table for the 0.95 quantile of the chi-square distribution with N degrees of
|
||||
freedom (contains values for N=1, ..., 9). Taken from MATLAB/Octave's chi2inv
|
||||
function and used as Mahalanobis gating threshold.
|
||||
"""
|
||||
chi2inv95 = {
|
||||
1: 3.8415,
|
||||
2: 5.9915,
|
||||
3: 7.8147,
|
||||
4: 9.4877,
|
||||
5: 11.070,
|
||||
6: 12.592,
|
||||
7: 14.067,
|
||||
8: 15.507,
|
||||
9: 16.919}
|
||||
|
||||
|
||||
class KalmanFilter(object):
|
||||
"""
|
||||
A simple Kalman filter for tracking bounding boxes in image space.
|
||||
|
||||
The 8-dimensional state space
|
||||
|
||||
x, y, a, h, vx, vy, va, vh
|
||||
|
||||
contains the bounding box center position (x, y), aspect ratio a, height h,
|
||||
and their respective velocities.
|
||||
|
||||
Object motion follows a constant velocity model. The bounding box location
|
||||
(x, y, a, h) is taken as direct observation of the state space (linear
|
||||
observation model).
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
ndim, dt = 4, 1.
|
||||
|
||||
# Create Kalman filter model matrices.
|
||||
self._motion_mat = np.eye(2 * ndim, 2 * ndim)
|
||||
for i in range(ndim):
|
||||
self._motion_mat[i, ndim + i] = dt
|
||||
self._update_mat = np.eye(ndim, 2 * ndim)
|
||||
|
||||
# Motion and observation uncertainty are chosen relative to the current
|
||||
# state estimate. These weights control the amount of uncertainty in
|
||||
# the model. This is a bit hacky.
|
||||
self._std_weight_position = 1. / 20
|
||||
self._std_weight_velocity = 1. / 160
|
||||
|
||||
def initiate(self, measurement):
|
||||
"""Create track from unassociated measurement.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
measurement : ndarray
|
||||
Bounding box coordinates (x, y, a, h) with center position (x, y),
|
||||
aspect ratio a, and height h.
|
||||
|
||||
Returns
|
||||
-------
|
||||
(ndarray, ndarray)
|
||||
Returns the mean vector (8 dimensional) and covariance matrix (8x8
|
||||
dimensional) of the new track. Unobserved velocities are initialized
|
||||
to 0 mean.
|
||||
|
||||
"""
|
||||
mean_pos = measurement
|
||||
mean_vel = np.zeros_like(mean_pos)
|
||||
mean = np.r_[mean_pos, mean_vel]
|
||||
|
||||
std = [
|
||||
2 * self._std_weight_position * measurement[3],
|
||||
2 * self._std_weight_position * measurement[3],
|
||||
1e-2,
|
||||
2 * self._std_weight_position * measurement[3],
|
||||
10 * self._std_weight_velocity * measurement[3],
|
||||
10 * self._std_weight_velocity * measurement[3],
|
||||
1e-5,
|
||||
10 * self._std_weight_velocity * measurement[3]]
|
||||
covariance = np.diag(np.square(std))
|
||||
return mean, covariance
|
||||
|
||||
def predict(self, mean, covariance):
|
||||
"""Run Kalman filter prediction step.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mean : ndarray
|
||||
The 8 dimensional mean vector of the object state at the previous
|
||||
time step.
|
||||
covariance : ndarray
|
||||
The 8x8 dimensional covariance matrix of the object state at the
|
||||
previous time step.
|
||||
|
||||
Returns
|
||||
-------
|
||||
(ndarray, ndarray)
|
||||
Returns the mean vector and covariance matrix of the predicted
|
||||
state. Unobserved velocities are initialized to 0 mean.
|
||||
|
||||
"""
|
||||
std_pos = [
|
||||
self._std_weight_position * mean[3],
|
||||
self._std_weight_position * mean[3],
|
||||
1e-2,
|
||||
self._std_weight_position * mean[3]]
|
||||
std_vel = [
|
||||
self._std_weight_velocity * mean[3],
|
||||
self._std_weight_velocity * mean[3],
|
||||
1e-5,
|
||||
self._std_weight_velocity * mean[3]]
|
||||
motion_cov = np.diag(np.square(np.r_[std_pos, std_vel]))
|
||||
|
||||
mean = np.dot(self._motion_mat, mean)
|
||||
covariance = np.linalg.multi_dot((
|
||||
self._motion_mat, covariance, self._motion_mat.T)) + motion_cov
|
||||
|
||||
return mean, covariance
|
||||
|
||||
def project(self, mean, covariance):
|
||||
"""Project state distribution to measurement space.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mean : ndarray
|
||||
The state's mean vector (8 dimensional array).
|
||||
covariance : ndarray
|
||||
The state's covariance matrix (8x8 dimensional).
|
||||
|
||||
Returns
|
||||
-------
|
||||
(ndarray, ndarray)
|
||||
Returns the projected mean and covariance matrix of the given state
|
||||
estimate.
|
||||
|
||||
"""
|
||||
std = [
|
||||
self._std_weight_position * mean[3],
|
||||
self._std_weight_position * mean[3],
|
||||
1e-1,
|
||||
self._std_weight_position * mean[3]]
|
||||
innovation_cov = np.diag(np.square(std))
|
||||
|
||||
mean = np.dot(self._update_mat, mean)
|
||||
covariance = np.linalg.multi_dot((
|
||||
self._update_mat, covariance, self._update_mat.T))
|
||||
return mean, covariance + innovation_cov
|
||||
|
||||
def update(self, mean, covariance, measurement):
|
||||
"""Run Kalman filter correction step.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mean : ndarray
|
||||
The predicted state's mean vector (8 dimensional).
|
||||
covariance : ndarray
|
||||
The state's covariance matrix (8x8 dimensional).
|
||||
measurement : ndarray
|
||||
The 4 dimensional measurement vector (x, y, a, h), where (x, y)
|
||||
is the center position, a the aspect ratio, and h the height of the
|
||||
bounding box.
|
||||
|
||||
Returns
|
||||
-------
|
||||
(ndarray, ndarray)
|
||||
Returns the measurement-corrected state distribution.
|
||||
|
||||
"""
|
||||
projected_mean, projected_cov = self.project(mean, covariance)
|
||||
|
||||
chol_factor, lower = scipy.linalg.cho_factor(
|
||||
projected_cov, lower=True, check_finite=False)
|
||||
kalman_gain = scipy.linalg.cho_solve(
|
||||
(chol_factor, lower), np.dot(covariance, self._update_mat.T).T,
|
||||
check_finite=False).T
|
||||
innovation = measurement - projected_mean
|
||||
|
||||
new_mean = mean + np.dot(innovation, kalman_gain.T)
|
||||
new_covariance = covariance - np.linalg.multi_dot((
|
||||
kalman_gain, projected_cov, kalman_gain.T))
|
||||
return new_mean, new_covariance
|
||||
|
||||
def gating_distance(self, mean, covariance, measurements,
|
||||
only_position=False):
|
||||
"""Compute gating distance between state distribution and measurements.
|
||||
|
||||
A suitable distance threshold can be obtained from `chi2inv95`. If
|
||||
`only_position` is False, the chi-square distribution has 4 degrees of
|
||||
freedom, otherwise 2.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mean : ndarray
|
||||
Mean vector over the state distribution (8 dimensional).
|
||||
covariance : ndarray
|
||||
Covariance of the state distribution (8x8 dimensional).
|
||||
measurements : ndarray
|
||||
An Nx4 dimensional matrix of N measurements, each in
|
||||
format (x, y, a, h) where (x, y) is the bounding box center
|
||||
position, a the aspect ratio, and h the height.
|
||||
only_position : Optional[bool]
|
||||
If True, distance computation is done with respect to the bounding
|
||||
box center position only.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
Returns an array of length N, where the i-th element contains the
|
||||
squared Mahalanobis distance between (mean, covariance) and
|
||||
`measurements[i]`.
|
||||
|
||||
"""
|
||||
mean, covariance = self.project(mean, covariance)
|
||||
if only_position:
|
||||
mean, covariance = mean[:2], covariance[:2, :2]
|
||||
measurements = measurements[:, :2]
|
||||
|
||||
cholesky_factor = np.linalg.cholesky(covariance)
|
||||
d = measurements - mean
|
||||
z = scipy.linalg.solve_triangular(
|
||||
cholesky_factor, d.T, lower=True, check_finite=False,
|
||||
overwrite_b=True)
|
||||
squared_maha = np.sum(z * z, axis=0)
|
||||
return squared_maha
|
||||
@ -0,0 +1,159 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
from __future__ import absolute_import
|
||||
import numpy as np
|
||||
# from sklearn.utils.linear_assignment_ import linear_assignment
|
||||
from scipy.optimize import linear_sum_assignment as linear_assignment
|
||||
from . import kalman_filter
|
||||
|
||||
|
||||
INFTY_COST = 1e+5
|
||||
|
||||
|
||||
def min_cost_matching(
|
||||
distance_metric, max_distance, tracks, detections, track_indices=None,
|
||||
detection_indices=None):
|
||||
if track_indices is None:
|
||||
track_indices = np.arange(len(tracks))
|
||||
if detection_indices is None:
|
||||
detection_indices = np.arange(len(detections))
|
||||
|
||||
if len(detection_indices) == 0 or len(track_indices) == 0:
|
||||
return [], track_indices, detection_indices # Nothing to match.
|
||||
|
||||
cost_matrix = distance_metric(
|
||||
tracks, detections, track_indices, detection_indices)
|
||||
cost_matrix[cost_matrix > max_distance] = max_distance + 1e-5
|
||||
|
||||
row_indices, col_indices = linear_assignment(cost_matrix)
|
||||
|
||||
matches, unmatched_tracks, unmatched_detections = [], [], []
|
||||
for col, detection_idx in enumerate(detection_indices):
|
||||
if col not in col_indices:
|
||||
unmatched_detections.append(detection_idx)
|
||||
for row, track_idx in enumerate(track_indices):
|
||||
if row not in row_indices:
|
||||
unmatched_tracks.append(track_idx)
|
||||
for row, col in zip(row_indices, col_indices):
|
||||
track_idx = track_indices[row]
|
||||
detection_idx = detection_indices[col]
|
||||
if cost_matrix[row, col] > max_distance:
|
||||
unmatched_tracks.append(track_idx)
|
||||
unmatched_detections.append(detection_idx)
|
||||
else:
|
||||
matches.append((track_idx, detection_idx))
|
||||
return matches, unmatched_tracks, unmatched_detections
|
||||
|
||||
|
||||
def matching_cascade(
|
||||
distance_metric, max_distance, cascade_depth, tracks, detections,
|
||||
track_indices=None, detection_indices=None):
|
||||
"""Run matching cascade.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
distance_metric : Callable[List[Track], List[Detection], List[int], List[int]) -> ndarray
|
||||
The distance metric is given a list of tracks and detections as well as
|
||||
a list of N track indices and M detection indices. The metric should
|
||||
return the NxM dimensional cost matrix, where element (i, j) is the
|
||||
association cost between the i-th track in the given track indices and
|
||||
the j-th detection in the given detection indices.
|
||||
max_distance : float
|
||||
Gating threshold. Associations with cost larger than this value are
|
||||
disregarded.
|
||||
cascade_depth: int
|
||||
The cascade depth, should be se to the maximum track age.
|
||||
tracks : List[track.Track]
|
||||
A list of predicted tracks at the current time step.
|
||||
detections : List[detection.Detection]
|
||||
A list of detections at the current time step.
|
||||
track_indices : Optional[List[int]]
|
||||
List of track indices that maps rows in `cost_matrix` to tracks in
|
||||
`tracks` (see description above). Defaults to all tracks.
|
||||
detection_indices : Optional[List[int]]
|
||||
List of detection indices that maps columns in `cost_matrix` to
|
||||
detections in `detections` (see description above). Defaults to all
|
||||
detections.
|
||||
|
||||
Returns
|
||||
-------
|
||||
(List[(int, int)], List[int], List[int])
|
||||
Returns a tuple with the following three entries:
|
||||
* A list of matched track and detection indices.
|
||||
* A list of unmatched track indices.
|
||||
* A list of unmatched detection indices.
|
||||
|
||||
"""
|
||||
if track_indices is None:
|
||||
track_indices = list(range(len(tracks)))
|
||||
if detection_indices is None:
|
||||
detection_indices = list(range(len(detections)))
|
||||
|
||||
unmatched_detections = detection_indices
|
||||
matches = []
|
||||
for level in range(cascade_depth):
|
||||
if len(unmatched_detections) == 0: # No detections left
|
||||
break
|
||||
|
||||
track_indices_l = [
|
||||
k for k in track_indices
|
||||
if tracks[k].time_since_update == 1 + level
|
||||
]
|
||||
if len(track_indices_l) == 0: # Nothing to match at this level
|
||||
continue
|
||||
|
||||
matches_l, _, unmatched_detections = \
|
||||
min_cost_matching(
|
||||
distance_metric, max_distance, tracks, detections,
|
||||
track_indices_l, unmatched_detections)
|
||||
matches += matches_l
|
||||
unmatched_tracks = list(set(track_indices) - set(k for k, _ in matches))
|
||||
return matches, unmatched_tracks, unmatched_detections
|
||||
|
||||
|
||||
def gate_cost_matrix(
|
||||
kf, cost_matrix, tracks, detections, track_indices, detection_indices,
|
||||
gated_cost=INFTY_COST, only_position=False):
|
||||
"""Invalidate infeasible entries in cost matrix based on the state
|
||||
distributions obtained by Kalman filtering.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
kf : The Kalman filter.
|
||||
cost_matrix : ndarray
|
||||
The NxM dimensional cost matrix, where N is the number of track indices
|
||||
and M is the number of detection indices, such that entry (i, j) is the
|
||||
association cost between `tracks[track_indices[i]]` and
|
||||
`detections[detection_indices[j]]`.
|
||||
tracks : List[track.Track]
|
||||
A list of predicted tracks at the current time step.
|
||||
detections : List[detection.Detection]
|
||||
A list of detections at the current time step.
|
||||
track_indices : List[int]
|
||||
List of track indices that maps rows in `cost_matrix` to tracks in
|
||||
`tracks` (see description above).
|
||||
detection_indices : List[int]
|
||||
List of detection indices that maps columns in `cost_matrix` to
|
||||
detections in `detections` (see description above).
|
||||
gated_cost : Optional[float]
|
||||
Entries in the cost matrix corresponding to infeasible associations are
|
||||
set this value. Defaults to a very large value.
|
||||
only_position : Optional[bool]
|
||||
If True, only the x, y position of the state distribution is considered
|
||||
during gating. Defaults to False.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
Returns the modified cost matrix.
|
||||
|
||||
"""
|
||||
gating_dim = 2 if only_position else 4
|
||||
gating_threshold = kalman_filter.chi2inv95[gating_dim]
|
||||
measurements = np.asarray(
|
||||
[detections[i].to_xyah() for i in detection_indices])
|
||||
for row, track_idx in enumerate(track_indices):
|
||||
track = tracks[track_idx]
|
||||
gating_distance = kf.gating_distance(
|
||||
track.mean, track.covariance, measurements, only_position)
|
||||
cost_matrix[row, gating_distance > gating_threshold] = gated_cost
|
||||
return cost_matrix
|
||||
@ -0,0 +1,177 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
import numpy as np
|
||||
|
||||
|
||||
def _pdist(a, b):
|
||||
"""Compute pair-wise squared distance between points in `a` and `b`.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
a : array_like
|
||||
An NxM matrix of N samples of dimensionality M.
|
||||
b : array_like
|
||||
An LxM matrix of L samples of dimensionality M.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
Returns a matrix of size len(a), len(b) such that eleement (i, j)
|
||||
contains the squared distance between `a[i]` and `b[j]`.
|
||||
|
||||
"""
|
||||
a, b = np.asarray(a), np.asarray(b)
|
||||
if len(a) == 0 or len(b) == 0:
|
||||
return np.zeros((len(a), len(b)))
|
||||
a2, b2 = np.square(a).sum(axis=1), np.square(b).sum(axis=1)
|
||||
r2 = -2. * np.dot(a, b.T) + a2[:, None] + b2[None, :]
|
||||
r2 = np.clip(r2, 0., float(np.inf))
|
||||
return r2
|
||||
|
||||
|
||||
def _cosine_distance(a, b, data_is_normalized=False):
|
||||
"""Compute pair-wise cosine distance between points in `a` and `b`.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
a : array_like
|
||||
An NxM matrix of N samples of dimensionality M.
|
||||
b : array_like
|
||||
An LxM matrix of L samples of dimensionality M.
|
||||
data_is_normalized : Optional[bool]
|
||||
If True, assumes rows in a and b are unit length vectors.
|
||||
Otherwise, a and b are explicitly normalized to lenght 1.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
Returns a matrix of size len(a), len(b) such that eleement (i, j)
|
||||
contains the squared distance between `a[i]` and `b[j]`.
|
||||
|
||||
"""
|
||||
if not data_is_normalized:
|
||||
a = np.asarray(a) / np.linalg.norm(a, axis=1, keepdims=True)
|
||||
b = np.asarray(b) / np.linalg.norm(b, axis=1, keepdims=True)
|
||||
return 1. - np.dot(a, b.T)
|
||||
|
||||
|
||||
def _nn_euclidean_distance(x, y):
|
||||
""" Helper function for nearest neighbor distance metric (Euclidean).
|
||||
|
||||
Parameters
|
||||
----------
|
||||
x : ndarray
|
||||
A matrix of N row-vectors (sample points).
|
||||
y : ndarray
|
||||
A matrix of M row-vectors (query points).
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
A vector of length M that contains for each entry in `y` the
|
||||
smallest Euclidean distance to a sample in `x`.
|
||||
|
||||
"""
|
||||
distances = _pdist(x, y)
|
||||
return np.maximum(0.0, distances.min(axis=0))
|
||||
|
||||
|
||||
def _nn_cosine_distance(x, y):
|
||||
""" Helper function for nearest neighbor distance metric (cosine).
|
||||
|
||||
Parameters
|
||||
----------
|
||||
x : ndarray
|
||||
A matrix of N row-vectors (sample points).
|
||||
y : ndarray
|
||||
A matrix of M row-vectors (query points).
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
A vector of length M that contains for each entry in `y` the
|
||||
smallest cosine distance to a sample in `x`.
|
||||
|
||||
"""
|
||||
distances = _cosine_distance(x, y)
|
||||
return distances.min(axis=0)
|
||||
|
||||
|
||||
class NearestNeighborDistanceMetric(object):
|
||||
"""
|
||||
A nearest neighbor distance metric that, for each target, returns
|
||||
the closest distance to any sample that has been observed so far.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
metric : str
|
||||
Either "euclidean" or "cosine".
|
||||
matching_threshold: float
|
||||
The matching threshold. Samples with larger distance are considered an
|
||||
invalid match.
|
||||
budget : Optional[int]
|
||||
If not None, fix samples per class to at most this number. Removes
|
||||
the oldest samples when the budget is reached.
|
||||
|
||||
Attributes
|
||||
----------
|
||||
samples : Dict[int -> List[ndarray]]
|
||||
A dictionary that maps from target identities to the list of samples
|
||||
that have been observed so far.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, metric, matching_threshold, budget=None):
|
||||
|
||||
|
||||
if metric == "euclidean":
|
||||
self._metric = _nn_euclidean_distance
|
||||
elif metric == "cosine":
|
||||
self._metric = _nn_cosine_distance
|
||||
else:
|
||||
raise ValueError(
|
||||
"Invalid metric; must be either 'euclidean' or 'cosine'")
|
||||
self.matching_threshold = matching_threshold
|
||||
self.budget = budget
|
||||
self.samples = {}
|
||||
|
||||
def partial_fit(self, features, targets, active_targets):
|
||||
"""Update the distance metric with new data.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
features : ndarray
|
||||
An NxM matrix of N features of dimensionality M.
|
||||
targets : ndarray
|
||||
An integer array of associated target identities.
|
||||
active_targets : List[int]
|
||||
A list of targets that are currently present in the scene.
|
||||
|
||||
"""
|
||||
for feature, target in zip(features, targets):
|
||||
self.samples.setdefault(target, []).append(feature)
|
||||
if self.budget is not None:
|
||||
self.samples[target] = self.samples[target][-self.budget:]
|
||||
self.samples = {k: self.samples[k] for k in active_targets}
|
||||
|
||||
def distance(self, features, targets):
|
||||
"""Compute distance between features and targets.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
features : ndarray
|
||||
An NxM matrix of N features of dimensionality M.
|
||||
targets : List[int]
|
||||
A list of targets to match the given `features` against.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
Returns a cost matrix of shape len(targets), len(features), where
|
||||
element (i, j) contains the closest squared distance between
|
||||
`targets[i]` and `features[j]`.
|
||||
|
||||
"""
|
||||
cost_matrix = np.zeros((len(targets), len(features)))
|
||||
for i, target in enumerate(targets):
|
||||
cost_matrix[i, :] = self._metric(self.samples[target], features)
|
||||
return cost_matrix
|
||||
@ -0,0 +1,73 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
import numpy as np
|
||||
import cv2
|
||||
|
||||
|
||||
def non_max_suppression(boxes, max_bbox_overlap, scores=None):
|
||||
"""Suppress overlapping detections.
|
||||
|
||||
Original code from [1]_ has been adapted to include confidence score.
|
||||
|
||||
.. [1] http://www.pyimagesearch.com/2015/02/16/
|
||||
faster-non-maximum-suppression-python/
|
||||
|
||||
Examples
|
||||
--------
|
||||
|
||||
>>> boxes = [d.roi for d in detections]
|
||||
>>> scores = [d.confidence for d in detections]
|
||||
>>> indices = non_max_suppression(boxes, max_bbox_overlap, scores)
|
||||
>>> detections = [detections[i] for i in indices]
|
||||
|
||||
Parameters
|
||||
----------
|
||||
boxes : ndarray
|
||||
Array of ROIs (x, y, width, height).
|
||||
max_bbox_overlap : float
|
||||
ROIs that overlap more than this values are suppressed.
|
||||
scores : Optional[array_like]
|
||||
Detector confidence score.
|
||||
|
||||
Returns
|
||||
-------
|
||||
List[int]
|
||||
Returns indices of detections that have survived non-maxima suppression.
|
||||
|
||||
"""
|
||||
if len(boxes) == 0:
|
||||
return []
|
||||
|
||||
boxes = boxes.astype(np.float32)
|
||||
pick = []
|
||||
|
||||
x1 = boxes[:, 0]
|
||||
y1 = boxes[:, 1]
|
||||
x2 = boxes[:, 2] + boxes[:, 0]
|
||||
y2 = boxes[:, 3] + boxes[:, 1]
|
||||
|
||||
area = (x2 - x1 + 1) * (y2 - y1 + 1)
|
||||
if scores is not None:
|
||||
idxs = np.argsort(scores)
|
||||
else:
|
||||
idxs = np.argsort(y2)
|
||||
|
||||
while len(idxs) > 0:
|
||||
last = len(idxs) - 1
|
||||
i = idxs[last]
|
||||
pick.append(i)
|
||||
|
||||
xx1 = np.maximum(x1[i], x1[idxs[:last]])
|
||||
yy1 = np.maximum(y1[i], y1[idxs[:last]])
|
||||
xx2 = np.minimum(x2[i], x2[idxs[:last]])
|
||||
yy2 = np.minimum(y2[i], y2[idxs[:last]])
|
||||
|
||||
w = np.maximum(0, xx2 - xx1 + 1)
|
||||
h = np.maximum(0, yy2 - yy1 + 1)
|
||||
|
||||
overlap = (w * h) / area[idxs[:last]]
|
||||
|
||||
idxs = np.delete(
|
||||
idxs, np.concatenate(
|
||||
([last], np.where(overlap > max_bbox_overlap)[0])))
|
||||
|
||||
return pick
|
||||
@ -0,0 +1,168 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
|
||||
|
||||
class TrackState:
|
||||
"""
|
||||
Enumeration type for the single target track state. Newly created tracks are
|
||||
classified as `tentative` until enough evidence has been collected. Then,
|
||||
the track state is changed to `confirmed`. Tracks that are no longer alive
|
||||
are classified as `deleted` to mark them for removal from the set of active
|
||||
tracks.
|
||||
|
||||
"""
|
||||
|
||||
Tentative = 1
|
||||
Confirmed = 2
|
||||
Deleted = 3
|
||||
|
||||
|
||||
class Track:
|
||||
"""
|
||||
A single target track with state space `(x, y, a, h)` and associated
|
||||
velocities, where `(x, y)` is the center of the bounding box, `a` is the
|
||||
aspect ratio and `h` is the height.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
mean : ndarray
|
||||
Mean vector of the initial state distribution.
|
||||
covariance : ndarray
|
||||
Covariance matrix of the initial state distribution.
|
||||
track_id : int
|
||||
A unique track identifier.
|
||||
n_init : int
|
||||
Number of consecutive detections before the track is confirmed. The
|
||||
track state is set to `Deleted` if a miss occurs within the first
|
||||
`n_init` frames.
|
||||
max_age : int
|
||||
The maximum number of consecutive misses before the track state is
|
||||
set to `Deleted`.
|
||||
feature : Optional[ndarray]
|
||||
Feature vector of the detection this track originates from. If not None,
|
||||
this feature is added to the `features` cache.
|
||||
|
||||
Attributes
|
||||
----------
|
||||
mean : ndarray
|
||||
Mean vector of the initial state distribution.
|
||||
covariance : ndarray
|
||||
Covariance matrix of the initial state distribution.
|
||||
track_id : int
|
||||
A unique track identifier.
|
||||
hits : int
|
||||
Total number of measurement updates.
|
||||
age : int
|
||||
Total number of frames since first occurance.
|
||||
time_since_update : int
|
||||
Total number of frames since last measurement update.
|
||||
state : TrackState
|
||||
The current track state.
|
||||
features : List[ndarray]
|
||||
A cache of features. On each measurement update, the associated feature
|
||||
vector is added to this list.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, mean, cls_, covariance, track_id, n_init, max_age,
|
||||
feature=None):
|
||||
self.mean = mean
|
||||
self.cls_ = cls_
|
||||
self.covariance = covariance
|
||||
self.track_id = track_id
|
||||
self.hits = 1
|
||||
self.age = 1
|
||||
self.time_since_update = 0
|
||||
|
||||
self.state = TrackState.Tentative
|
||||
self.features = []
|
||||
if feature is not None:
|
||||
self.features.append(feature)
|
||||
|
||||
self._n_init = n_init
|
||||
self._max_age = max_age
|
||||
|
||||
def to_tlwh(self):
|
||||
"""Get current position in bounding box format `(top left x, top left y,
|
||||
width, height)`.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
The bounding box.
|
||||
|
||||
"""
|
||||
ret = self.mean[:4].copy()
|
||||
ret[2] *= ret[3]
|
||||
ret[:2] -= ret[2:] / 2
|
||||
return ret
|
||||
|
||||
def to_tlbr(self):
|
||||
"""Get current position in bounding box format `(min x, miny, max x,
|
||||
max y)`.
|
||||
|
||||
Returns
|
||||
-------
|
||||
ndarray
|
||||
The bounding box.
|
||||
|
||||
"""
|
||||
ret = self.to_tlwh()
|
||||
ret[2:] = ret[:2] + ret[2:]
|
||||
return ret
|
||||
|
||||
def predict(self, kf):
|
||||
"""Propagate the state distribution to the current time step using a
|
||||
Kalman filter prediction step.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
kf : kalman_filter.KalmanFilter
|
||||
The Kalman filter.
|
||||
|
||||
"""
|
||||
self.mean, self.covariance = kf.predict(self.mean, self.covariance)
|
||||
self.age += 1
|
||||
self.time_since_update += 1
|
||||
|
||||
def update(self, kf, detection):
|
||||
"""Perform Kalman filter measurement update step and update the feature
|
||||
cache.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
kf : kalman_filter.KalmanFilter
|
||||
The Kalman filter.
|
||||
detection : Detection
|
||||
The associated detection.
|
||||
|
||||
"""
|
||||
self.mean, self.covariance = kf.update(
|
||||
self.mean, self.covariance, detection.to_xyah())
|
||||
self.features.append(detection.feature)
|
||||
self.cls_ = detection.cls_
|
||||
|
||||
self.hits += 1
|
||||
self.time_since_update = 0
|
||||
if self.state == TrackState.Tentative and self.hits >= self._n_init:
|
||||
self.state = TrackState.Confirmed
|
||||
|
||||
def mark_missed(self):
|
||||
"""Mark this track as missed (no association at the current time step).
|
||||
"""
|
||||
if self.state == TrackState.Tentative:
|
||||
self.state = TrackState.Deleted
|
||||
elif self.time_since_update > self._max_age:
|
||||
self.state = TrackState.Deleted
|
||||
|
||||
def is_tentative(self):
|
||||
"""Returns True if this track is tentative (unconfirmed).
|
||||
"""
|
||||
return self.state == TrackState.Tentative
|
||||
|
||||
def is_confirmed(self):
|
||||
"""Returns True if this track is confirmed."""
|
||||
return self.state == TrackState.Confirmed
|
||||
|
||||
def is_deleted(self):
|
||||
"""Returns True if this track is dead and should be deleted."""
|
||||
return self.state == TrackState.Deleted
|
||||
@ -0,0 +1,109 @@
|
||||
# vim: expandtab:ts=4:sw=4
|
||||
from __future__ import absolute_import
|
||||
import numpy as np
|
||||
from . import kalman_filter
|
||||
from . import linear_assignment
|
||||
from . import iou_matching
|
||||
from .track import Track
|
||||
|
||||
|
||||
class Tracker:
|
||||
|
||||
def __init__(self, metric, max_iou_distance=0.7, max_age=70, n_init=3):
|
||||
self.metric = metric
|
||||
self.max_iou_distance = max_iou_distance
|
||||
self.max_age = max_age
|
||||
self.n_init = n_init
|
||||
|
||||
self.kf = kalman_filter.KalmanFilter()
|
||||
self.tracks = []
|
||||
self._next_id = 1
|
||||
|
||||
def predict(self):
|
||||
"""Propagate track state distributions one time step forward.
|
||||
|
||||
This function should be called once every time step, before `update`.
|
||||
"""
|
||||
for track in self.tracks:
|
||||
track.predict(self.kf)
|
||||
|
||||
def update(self, detections):
|
||||
"""Perform measurement update and track management.
|
||||
|
||||
Parameters
|
||||
----------
|
||||
detections : List[deep_sort.detection.Detection]
|
||||
A list of detections at the current time step.
|
||||
|
||||
"""
|
||||
# Run matching cascade.
|
||||
matches, unmatched_tracks, unmatched_detections = \
|
||||
self._match(detections)
|
||||
|
||||
# Update track set.
|
||||
for track_idx, detection_idx in matches:
|
||||
self.tracks[track_idx].update(
|
||||
self.kf, detections[detection_idx])
|
||||
for track_idx in unmatched_tracks:
|
||||
self.tracks[track_idx].mark_missed()
|
||||
for detection_idx in unmatched_detections:
|
||||
self._initiate_track(detections[detection_idx])
|
||||
self.tracks = [t for t in self.tracks if not t.is_deleted()]
|
||||
|
||||
# Update distance metric.
|
||||
active_targets = [t.track_id for t in self.tracks if t.is_confirmed()]
|
||||
features, targets = [], []
|
||||
for track in self.tracks:
|
||||
if not track.is_confirmed():
|
||||
continue
|
||||
features += track.features
|
||||
targets += [track.track_id for _ in track.features]
|
||||
track.features = []
|
||||
self.metric.partial_fit(
|
||||
np.asarray(features), np.asarray(targets), active_targets)
|
||||
|
||||
def _match(self, detections):
|
||||
|
||||
def gated_metric(tracks, dets, track_indices, detection_indices):
|
||||
features = np.array([dets[i].feature for i in detection_indices])
|
||||
targets = np.array([tracks[i].track_id for i in track_indices])
|
||||
cost_matrix = self.metric.distance(features, targets)
|
||||
cost_matrix = linear_assignment.gate_cost_matrix(
|
||||
self.kf, cost_matrix, tracks, dets, track_indices,
|
||||
detection_indices)
|
||||
|
||||
return cost_matrix
|
||||
|
||||
# Split track set into confirmed and unconfirmed tracks.
|
||||
confirmed_tracks = [
|
||||
i for i, t in enumerate(self.tracks) if t.is_confirmed()]
|
||||
unconfirmed_tracks = [
|
||||
i for i, t in enumerate(self.tracks) if not t.is_confirmed()]
|
||||
|
||||
# Associate confirmed tracks using appearance features.
|
||||
matches_a, unmatched_tracks_a, unmatched_detections = \
|
||||
linear_assignment.matching_cascade(
|
||||
gated_metric, self.metric.matching_threshold, self.max_age,
|
||||
self.tracks, detections, confirmed_tracks)
|
||||
|
||||
# Associate remaining tracks together with unconfirmed tracks using IOU.
|
||||
iou_track_candidates = unconfirmed_tracks + [
|
||||
k for k in unmatched_tracks_a if
|
||||
self.tracks[k].time_since_update == 1]
|
||||
unmatched_tracks_a = [
|
||||
k for k in unmatched_tracks_a if
|
||||
self.tracks[k].time_since_update != 1]
|
||||
matches_b, unmatched_tracks_b, unmatched_detections = \
|
||||
linear_assignment.min_cost_matching(
|
||||
iou_matching.iou_cost, self.max_iou_distance, self.tracks,
|
||||
detections, iou_track_candidates, unmatched_detections)
|
||||
matches = matches_a + matches_b
|
||||
unmatched_tracks = list(set(unmatched_tracks_a + unmatched_tracks_b))
|
||||
return matches, unmatched_tracks, unmatched_detections
|
||||
|
||||
def _initiate_track(self, detection):
|
||||
mean, covariance = self.kf.initiate(detection.to_xyah())
|
||||
self.tracks.append(Track(
|
||||
mean, detection.cls_, covariance, self._next_id, self.n_init, self.max_age,
|
||||
detection.feature))
|
||||
self._next_id += 1
|
||||
@ -0,0 +1,13 @@
|
||||
from os import environ
|
||||
|
||||
|
||||
def assert_in(file, files_to_check):
|
||||
if file not in files_to_check:
|
||||
raise AssertionError("{} does not exist in the list".format(str(file)))
|
||||
return True
|
||||
|
||||
|
||||
def assert_in_env(check_list: list):
|
||||
for item in check_list:
|
||||
assert_in(item, environ.keys())
|
||||
return True
|
||||
@ -0,0 +1,36 @@
|
||||
import numpy as np
|
||||
import cv2
|
||||
|
||||
palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1)
|
||||
|
||||
|
||||
def compute_color_for_labels(label):
|
||||
"""
|
||||
Simple function that adds fixed color depending on the class
|
||||
"""
|
||||
color = [int((p * (label ** 2 - label + 1)) % 255) for p in palette]
|
||||
return tuple(color)
|
||||
|
||||
|
||||
def draw_boxes(img, bbox, identities=None, offset=(0,0)):
|
||||
for i,box in enumerate(bbox):
|
||||
x1,y1,x2,y2 = [int(i) for i in box]
|
||||
x1 += offset[0]
|
||||
x2 += offset[0]
|
||||
y1 += offset[1]
|
||||
y2 += offset[1]
|
||||
# box text and bar
|
||||
id = int(identities[i]) if identities is not None else 0
|
||||
color = compute_color_for_labels(id)
|
||||
label = '{}{:d}'.format("", id)
|
||||
t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 2 , 2)[0]
|
||||
cv2.rectangle(img,(x1, y1),(x2,y2),color,3)
|
||||
cv2.rectangle(img,(x1, y1),(x1+t_size[0]+3,y1+t_size[1]+4), color,-1)
|
||||
cv2.putText(img,label,(x1,y1+t_size[1]+4), cv2.FONT_HERSHEY_PLAIN, 2, [255,255,255], 2)
|
||||
return img
|
||||
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
for i in range(82):
|
||||
print(compute_color_for_labels(i))
|
||||
@ -0,0 +1,103 @@
|
||||
import os
|
||||
import numpy as np
|
||||
import copy
|
||||
import motmetrics as mm
|
||||
mm.lap.default_solver = 'lap'
|
||||
from utils.io import read_results, unzip_objs
|
||||
|
||||
|
||||
class Evaluator(object):
|
||||
|
||||
def __init__(self, data_root, seq_name, data_type):
|
||||
self.data_root = data_root
|
||||
self.seq_name = seq_name
|
||||
self.data_type = data_type
|
||||
|
||||
self.load_annotations()
|
||||
self.reset_accumulator()
|
||||
|
||||
def load_annotations(self):
|
||||
assert self.data_type == 'mot'
|
||||
|
||||
gt_filename = os.path.join(self.data_root, self.seq_name, 'gt', 'gt.txt')
|
||||
self.gt_frame_dict = read_results(gt_filename, self.data_type, is_gt=True)
|
||||
self.gt_ignore_frame_dict = read_results(gt_filename, self.data_type, is_ignore=True)
|
||||
|
||||
def reset_accumulator(self):
|
||||
self.acc = mm.MOTAccumulator(auto_id=True)
|
||||
|
||||
def eval_frame(self, frame_id, trk_tlwhs, trk_ids, rtn_events=False):
|
||||
# results
|
||||
trk_tlwhs = np.copy(trk_tlwhs)
|
||||
trk_ids = np.copy(trk_ids)
|
||||
|
||||
# gts
|
||||
gt_objs = self.gt_frame_dict.get(frame_id, [])
|
||||
gt_tlwhs, gt_ids = unzip_objs(gt_objs)[:2]
|
||||
|
||||
# ignore boxes
|
||||
ignore_objs = self.gt_ignore_frame_dict.get(frame_id, [])
|
||||
ignore_tlwhs = unzip_objs(ignore_objs)[0]
|
||||
|
||||
|
||||
# remove ignored results
|
||||
keep = np.ones(len(trk_tlwhs), dtype=bool)
|
||||
iou_distance = mm.distances.iou_matrix(ignore_tlwhs, trk_tlwhs, max_iou=0.5)
|
||||
if len(iou_distance) > 0:
|
||||
match_is, match_js = mm.lap.linear_sum_assignment(iou_distance)
|
||||
match_is, match_js = map(lambda a: np.asarray(a, dtype=int), [match_is, match_js])
|
||||
match_ious = iou_distance[match_is, match_js]
|
||||
|
||||
match_js = np.asarray(match_js, dtype=int)
|
||||
match_js = match_js[np.logical_not(np.isnan(match_ious))]
|
||||
keep[match_js] = False
|
||||
trk_tlwhs = trk_tlwhs[keep]
|
||||
trk_ids = trk_ids[keep]
|
||||
|
||||
# get distance matrix
|
||||
iou_distance = mm.distances.iou_matrix(gt_tlwhs, trk_tlwhs, max_iou=0.5)
|
||||
|
||||
# acc
|
||||
self.acc.update(gt_ids, trk_ids, iou_distance)
|
||||
|
||||
if rtn_events and iou_distance.size > 0 and hasattr(self.acc, 'last_mot_events'):
|
||||
events = self.acc.last_mot_events # only supported by https://github.com/longcw/py-motmetrics
|
||||
else:
|
||||
events = None
|
||||
return events
|
||||
|
||||
def eval_file(self, filename):
|
||||
self.reset_accumulator()
|
||||
|
||||
result_frame_dict = read_results(filename, self.data_type, is_gt=False)
|
||||
frames = sorted(list(set(self.gt_frame_dict.keys()) | set(result_frame_dict.keys())))
|
||||
for frame_id in frames:
|
||||
trk_objs = result_frame_dict.get(frame_id, [])
|
||||
trk_tlwhs, trk_ids = unzip_objs(trk_objs)[:2]
|
||||
self.eval_frame(frame_id, trk_tlwhs, trk_ids, rtn_events=False)
|
||||
|
||||
return self.acc
|
||||
|
||||
@staticmethod
|
||||
def get_summary(accs, names, metrics=('mota', 'num_switches', 'idp', 'idr', 'idf1', 'precision', 'recall')):
|
||||
names = copy.deepcopy(names)
|
||||
if metrics is None:
|
||||
metrics = mm.metrics.motchallenge_metrics
|
||||
metrics = copy.deepcopy(metrics)
|
||||
|
||||
mh = mm.metrics.create()
|
||||
summary = mh.compute_many(
|
||||
accs,
|
||||
metrics=metrics,
|
||||
names=names,
|
||||
generate_overall=True
|
||||
)
|
||||
|
||||
return summary
|
||||
|
||||
@staticmethod
|
||||
def save_summary(summary, filename):
|
||||
import pandas as pd
|
||||
writer = pd.ExcelWriter(filename)
|
||||
summary.to_excel(writer)
|
||||
writer.save()
|
||||
@ -0,0 +1,133 @@
|
||||
import os
|
||||
from typing import Dict
|
||||
import numpy as np
|
||||
|
||||
# from utils.log import get_logger
|
||||
|
||||
|
||||
def write_results(filename, results, data_type):
|
||||
if data_type == 'mot':
|
||||
save_format = '{frame},{id},{x1},{y1},{w},{h},-1,-1,-1,-1\n'
|
||||
elif data_type == 'kitti':
|
||||
save_format = '{frame} {id} pedestrian 0 0 -10 {x1} {y1} {x2} {y2} -10 -10 -10 -1000 -1000 -1000 -10\n'
|
||||
else:
|
||||
raise ValueError(data_type)
|
||||
|
||||
with open(filename, 'w') as f:
|
||||
for frame_id, tlwhs, track_ids in results:
|
||||
if data_type == 'kitti':
|
||||
frame_id -= 1
|
||||
for tlwh, track_id in zip(tlwhs, track_ids):
|
||||
if track_id < 0:
|
||||
continue
|
||||
x1, y1, w, h = tlwh
|
||||
x2, y2 = x1 + w, y1 + h
|
||||
line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h)
|
||||
f.write(line)
|
||||
|
||||
|
||||
# def write_results(filename, results_dict: Dict, data_type: str):
|
||||
# if not filename:
|
||||
# return
|
||||
# path = os.path.dirname(filename)
|
||||
# if not os.path.exists(path):
|
||||
# os.makedirs(path)
|
||||
|
||||
# if data_type in ('mot', 'mcmot', 'lab'):
|
||||
# save_format = '{frame},{id},{x1},{y1},{w},{h},1,-1,-1,-1\n'
|
||||
# elif data_type == 'kitti':
|
||||
# save_format = '{frame} {id} pedestrian -1 -1 -10 {x1} {y1} {x2} {y2} -1 -1 -1 -1000 -1000 -1000 -10 {score}\n'
|
||||
# else:
|
||||
# raise ValueError(data_type)
|
||||
|
||||
# with open(filename, 'w') as f:
|
||||
# for frame_id, frame_data in results_dict.items():
|
||||
# if data_type == 'kitti':
|
||||
# frame_id -= 1
|
||||
# for tlwh, track_id in frame_data:
|
||||
# if track_id < 0:
|
||||
# continue
|
||||
# x1, y1, w, h = tlwh
|
||||
# x2, y2 = x1 + w, y1 + h
|
||||
# line = save_format.format(frame=frame_id, id=track_id, x1=x1, y1=y1, x2=x2, y2=y2, w=w, h=h, score=1.0)
|
||||
# f.write(line)
|
||||
# logger.info('Save results to {}'.format(filename))
|
||||
|
||||
|
||||
def read_results(filename, data_type: str, is_gt=False, is_ignore=False):
|
||||
if data_type in ('mot', 'lab'):
|
||||
read_fun = read_mot_results
|
||||
else:
|
||||
raise ValueError('Unknown data type: {}'.format(data_type))
|
||||
|
||||
return read_fun(filename, is_gt, is_ignore)
|
||||
|
||||
|
||||
"""
|
||||
labels={'ped', ... % 1
|
||||
'person_on_vhcl', ... % 2
|
||||
'car', ... % 3
|
||||
'bicycle', ... % 4
|
||||
'mbike', ... % 5
|
||||
'non_mot_vhcl', ... % 6
|
||||
'static_person', ... % 7
|
||||
'distractor', ... % 8
|
||||
'occluder', ... % 9
|
||||
'occluder_on_grnd', ... %10
|
||||
'occluder_full', ... % 11
|
||||
'reflection', ... % 12
|
||||
'crowd' ... % 13
|
||||
};
|
||||
"""
|
||||
|
||||
|
||||
def read_mot_results(filename, is_gt, is_ignore):
|
||||
valid_labels = {1}
|
||||
ignore_labels = {2, 7, 8, 12}
|
||||
results_dict = dict()
|
||||
if os.path.isfile(filename):
|
||||
with open(filename, 'r') as f:
|
||||
for line in f.readlines():
|
||||
linelist = line.split(',')
|
||||
if len(linelist) < 7:
|
||||
continue
|
||||
fid = int(linelist[0])
|
||||
if fid < 1:
|
||||
continue
|
||||
results_dict.setdefault(fid, list())
|
||||
|
||||
if is_gt:
|
||||
if 'MOT16-' in filename or 'MOT17-' in filename:
|
||||
label = int(float(linelist[7]))
|
||||
mark = int(float(linelist[6]))
|
||||
if mark == 0 or label not in valid_labels:
|
||||
continue
|
||||
score = 1
|
||||
elif is_ignore:
|
||||
if 'MOT16-' in filename or 'MOT17-' in filename:
|
||||
label = int(float(linelist[7]))
|
||||
vis_ratio = float(linelist[8])
|
||||
if label not in ignore_labels and vis_ratio >= 0:
|
||||
continue
|
||||
else:
|
||||
continue
|
||||
score = 1
|
||||
else:
|
||||
score = float(linelist[6])
|
||||
|
||||
tlwh = tuple(map(float, linelist[2:6]))
|
||||
target_id = int(linelist[1])
|
||||
|
||||
results_dict[fid].append((tlwh, target_id, score))
|
||||
|
||||
return results_dict
|
||||
|
||||
|
||||
def unzip_objs(objs):
|
||||
if len(objs) > 0:
|
||||
tlwhs, ids, scores = zip(*objs)
|
||||
else:
|
||||
tlwhs, ids, scores = [], [], []
|
||||
tlwhs = np.asarray(tlwhs, dtype=float).reshape(-1, 4)
|
||||
|
||||
return tlwhs, ids, scores
|
||||
@ -0,0 +1,383 @@
|
||||
"""
|
||||
References:
|
||||
https://medium.com/analytics-vidhya/creating-a-custom-logging-mechanism-for-real-time-object-detection-using-tdd-4ca2cfcd0a2f
|
||||
"""
|
||||
import json
|
||||
from os import makedirs
|
||||
from os.path import exists, join
|
||||
from datetime import datetime
|
||||
|
||||
|
||||
class JsonMeta(object):
|
||||
HOURS = 3
|
||||
MINUTES = 59
|
||||
SECONDS = 59
|
||||
PATH_TO_SAVE = 'LOGS'
|
||||
DEFAULT_FILE_NAME = 'remaining'
|
||||
|
||||
|
||||
class BaseJsonLogger(object):
|
||||
"""
|
||||
This is the base class that returns __dict__ of its own
|
||||
it also returns the dicts of objects in the attributes that are list instances
|
||||
|
||||
"""
|
||||
|
||||
def dic(self):
|
||||
# returns dicts of objects
|
||||
out = {}
|
||||
for k, v in self.__dict__.items():
|
||||
if hasattr(v, 'dic'):
|
||||
out[k] = v.dic()
|
||||
elif isinstance(v, list):
|
||||
out[k] = self.list(v)
|
||||
else:
|
||||
out[k] = v
|
||||
return out
|
||||
|
||||
@staticmethod
|
||||
def list(values):
|
||||
# applies the dic method on items in the list
|
||||
return [v.dic() if hasattr(v, 'dic') else v for v in values]
|
||||
|
||||
|
||||
class Label(BaseJsonLogger):
|
||||
"""
|
||||
For each bounding box there are various categories with confidences. Label class keeps track of that information.
|
||||
"""
|
||||
|
||||
def __init__(self, category: str, confidence: float):
|
||||
self.category = category
|
||||
self.confidence = confidence
|
||||
|
||||
|
||||
class Bbox(BaseJsonLogger):
|
||||
"""
|
||||
This module stores the information for each frame and use them in JsonParser
|
||||
Attributes:
|
||||
labels (list): List of label module.
|
||||
top (int):
|
||||
left (int):
|
||||
width (int):
|
||||
height (int):
|
||||
|
||||
Args:
|
||||
bbox_id (float):
|
||||
top (int):
|
||||
left (int):
|
||||
width (int):
|
||||
height (int):
|
||||
|
||||
References:
|
||||
Check Label module for better understanding.
|
||||
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, bbox_id, top, left, width, height):
|
||||
self.labels = []
|
||||
self.bbox_id = bbox_id
|
||||
self.top = top
|
||||
self.left = left
|
||||
self.width = width
|
||||
self.height = height
|
||||
|
||||
def add_label(self, category, confidence):
|
||||
# adds category and confidence only if top_k is not exceeded.
|
||||
self.labels.append(Label(category, confidence))
|
||||
|
||||
def labels_full(self, value):
|
||||
return len(self.labels) == value
|
||||
|
||||
|
||||
class Frame(BaseJsonLogger):
|
||||
"""
|
||||
This module stores the information for each frame and use them in JsonParser
|
||||
Attributes:
|
||||
timestamp (float): The elapsed time of captured frame
|
||||
frame_id (int): The frame number of the captured video
|
||||
bboxes (list of Bbox objects): Stores the list of bbox objects.
|
||||
|
||||
References:
|
||||
Check Bbox class for better information
|
||||
|
||||
Args:
|
||||
timestamp (float):
|
||||
frame_id (int):
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, frame_id: int, timestamp: float = None):
|
||||
self.frame_id = frame_id
|
||||
self.timestamp = timestamp
|
||||
self.bboxes = []
|
||||
|
||||
def add_bbox(self, bbox_id: int, top: int, left: int, width: int, height: int):
|
||||
bboxes_ids = [bbox.bbox_id for bbox in self.bboxes]
|
||||
if bbox_id not in bboxes_ids:
|
||||
self.bboxes.append(Bbox(bbox_id, top, left, width, height))
|
||||
else:
|
||||
raise ValueError("Frame with id: {} already has a Bbox with id: {}".format(self.frame_id, bbox_id))
|
||||
|
||||
def add_label_to_bbox(self, bbox_id: int, category: str, confidence: float):
|
||||
bboxes = {bbox.id: bbox for bbox in self.bboxes}
|
||||
if bbox_id in bboxes.keys():
|
||||
res = bboxes.get(bbox_id)
|
||||
res.add_label(category, confidence)
|
||||
else:
|
||||
raise ValueError('the bbox with id: {} does not exists!'.format(bbox_id))
|
||||
|
||||
|
||||
class BboxToJsonLogger(BaseJsonLogger):
|
||||
"""
|
||||
ُ This module is designed to automate the task of logging jsons. An example json is used
|
||||
to show the contents of json file shortly
|
||||
Example:
|
||||
{
|
||||
"video_details": {
|
||||
"frame_width": 1920,
|
||||
"frame_height": 1080,
|
||||
"frame_rate": 20,
|
||||
"video_name": "/home/gpu/codes/MSD/pedestrian_2/project/public/camera1.avi"
|
||||
},
|
||||
"frames": [
|
||||
{
|
||||
"frame_id": 329,
|
||||
"timestamp": 3365.1254
|
||||
"bboxes": [
|
||||
{
|
||||
"labels": [
|
||||
{
|
||||
"category": "pedestrian",
|
||||
"confidence": 0.9
|
||||
}
|
||||
],
|
||||
"bbox_id": 0,
|
||||
"top": 1257,
|
||||
"left": 138,
|
||||
"width": 68,
|
||||
"height": 109
|
||||
}
|
||||
]
|
||||
}],
|
||||
|
||||
Attributes:
|
||||
frames (dict): It's a dictionary that maps each frame_id to json attributes.
|
||||
video_details (dict): information about video file.
|
||||
top_k_labels (int): shows the allowed number of labels
|
||||
start_time (datetime object): we use it to automate the json output by time.
|
||||
|
||||
Args:
|
||||
top_k_labels (int): shows the allowed number of labels
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, top_k_labels: int = 1):
|
||||
self.frames = {}
|
||||
self.video_details = self.video_details = dict(frame_width=None, frame_height=None, frame_rate=None,
|
||||
video_name=None)
|
||||
self.top_k_labels = top_k_labels
|
||||
self.start_time = datetime.now()
|
||||
|
||||
def set_top_k(self, value):
|
||||
self.top_k_labels = value
|
||||
|
||||
def frame_exists(self, frame_id: int) -> bool:
|
||||
"""
|
||||
Args:
|
||||
frame_id (int):
|
||||
|
||||
Returns:
|
||||
bool: true if frame_id is recognized
|
||||
"""
|
||||
return frame_id in self.frames.keys()
|
||||
|
||||
def add_frame(self, frame_id: int, timestamp: float = None) -> None:
|
||||
"""
|
||||
Args:
|
||||
frame_id (int):
|
||||
timestamp (float): opencv captured frame time property
|
||||
|
||||
Raises:
|
||||
ValueError: if frame_id would not exist in class frames attribute
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
"""
|
||||
if not self.frame_exists(frame_id):
|
||||
self.frames[frame_id] = Frame(frame_id, timestamp)
|
||||
else:
|
||||
raise ValueError("Frame id: {} already exists".format(frame_id))
|
||||
|
||||
def bbox_exists(self, frame_id: int, bbox_id: int) -> bool:
|
||||
"""
|
||||
Args:
|
||||
frame_id:
|
||||
bbox_id:
|
||||
|
||||
Returns:
|
||||
bool: if bbox exists in frame bboxes list
|
||||
"""
|
||||
bboxes = []
|
||||
if self.frame_exists(frame_id=frame_id):
|
||||
bboxes = [bbox.bbox_id for bbox in self.frames[frame_id].bboxes]
|
||||
return bbox_id in bboxes
|
||||
|
||||
def find_bbox(self, frame_id: int, bbox_id: int):
|
||||
"""
|
||||
|
||||
Args:
|
||||
frame_id:
|
||||
bbox_id:
|
||||
|
||||
Returns:
|
||||
bbox_id (int):
|
||||
|
||||
Raises:
|
||||
ValueError: if bbox_id does not exist in the bbox list of specific frame.
|
||||
"""
|
||||
if not self.bbox_exists(frame_id, bbox_id):
|
||||
raise ValueError("frame with id: {} does not contain bbox with id: {}".format(frame_id, bbox_id))
|
||||
bboxes = {bbox.bbox_id: bbox for bbox in self.frames[frame_id].bboxes}
|
||||
return bboxes.get(bbox_id)
|
||||
|
||||
def add_bbox_to_frame(self, frame_id: int, bbox_id: int, top: int, left: int, width: int, height: int) -> None:
|
||||
"""
|
||||
|
||||
Args:
|
||||
frame_id (int):
|
||||
bbox_id (int):
|
||||
top (int):
|
||||
left (int):
|
||||
width (int):
|
||||
height (int):
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
Raises:
|
||||
ValueError: if bbox_id already exist in frame information with frame_id
|
||||
ValueError: if frame_id does not exist in frames attribute
|
||||
"""
|
||||
if self.frame_exists(frame_id):
|
||||
frame = self.frames[frame_id]
|
||||
if not self.bbox_exists(frame_id, bbox_id):
|
||||
frame.add_bbox(bbox_id, top, left, width, height)
|
||||
else:
|
||||
raise ValueError(
|
||||
"frame with frame_id: {} already contains the bbox with id: {} ".format(frame_id, bbox_id))
|
||||
else:
|
||||
raise ValueError("frame with frame_id: {} does not exist".format(frame_id))
|
||||
|
||||
def add_label_to_bbox(self, frame_id: int, bbox_id: int, category: str, confidence: float):
|
||||
"""
|
||||
Args:
|
||||
frame_id:
|
||||
bbox_id:
|
||||
category:
|
||||
confidence: the confidence value returned from yolo detection
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
Raises:
|
||||
ValueError: if labels quota (top_k_labels) exceeds.
|
||||
"""
|
||||
bbox = self.find_bbox(frame_id, bbox_id)
|
||||
if not bbox.labels_full(self.top_k_labels):
|
||||
bbox.add_label(category, confidence)
|
||||
else:
|
||||
raise ValueError("labels in frame_id: {}, bbox_id: {} is fulled".format(frame_id, bbox_id))
|
||||
|
||||
def add_video_details(self, frame_width: int = None, frame_height: int = None, frame_rate: int = None,
|
||||
video_name: str = None):
|
||||
self.video_details['frame_width'] = frame_width
|
||||
self.video_details['frame_height'] = frame_height
|
||||
self.video_details['frame_rate'] = frame_rate
|
||||
self.video_details['video_name'] = video_name
|
||||
|
||||
def output(self):
|
||||
output = {'video_details': self.video_details}
|
||||
result = list(self.frames.values())
|
||||
output['frames'] = [item.dic() for item in result]
|
||||
return output
|
||||
|
||||
def json_output(self, output_name):
|
||||
"""
|
||||
Args:
|
||||
output_name:
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
Notes:
|
||||
It creates the json output with `output_name` name.
|
||||
"""
|
||||
if not output_name.endswith('.json'):
|
||||
output_name += '.json'
|
||||
with open(output_name, 'w') as file:
|
||||
json.dump(self.output(), file)
|
||||
file.close()
|
||||
|
||||
def set_start(self):
|
||||
self.start_time = datetime.now()
|
||||
|
||||
def schedule_output_by_time(self, output_dir=JsonMeta.PATH_TO_SAVE, hours: int = 0, minutes: int = 0,
|
||||
seconds: int = 60) -> None:
|
||||
"""
|
||||
Notes:
|
||||
Creates folder and then periodically stores the jsons on that address.
|
||||
|
||||
Args:
|
||||
output_dir (str): the directory where output files will be stored
|
||||
hours (int):
|
||||
minutes (int):
|
||||
seconds (int):
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
"""
|
||||
end = datetime.now()
|
||||
interval = 0
|
||||
interval += abs(min([hours, JsonMeta.HOURS]) * 3600)
|
||||
interval += abs(min([minutes, JsonMeta.MINUTES]) * 60)
|
||||
interval += abs(min([seconds, JsonMeta.SECONDS]))
|
||||
diff = (end - self.start_time).seconds
|
||||
|
||||
if diff > interval:
|
||||
output_name = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '.json'
|
||||
if not exists(output_dir):
|
||||
makedirs(output_dir)
|
||||
output = join(output_dir, output_name)
|
||||
self.json_output(output_name=output)
|
||||
self.frames = {}
|
||||
self.start_time = datetime.now()
|
||||
|
||||
def schedule_output_by_frames(self, frames_quota, frame_counter, output_dir=JsonMeta.PATH_TO_SAVE):
|
||||
"""
|
||||
saves as the number of frames quota increases higher.
|
||||
:param frames_quota:
|
||||
:param frame_counter:
|
||||
:param output_dir:
|
||||
:return:
|
||||
"""
|
||||
pass
|
||||
|
||||
def flush(self, output_dir):
|
||||
"""
|
||||
Notes:
|
||||
We use this function to output jsons whenever possible.
|
||||
like the time that we exit the while loop of opencv.
|
||||
|
||||
Args:
|
||||
output_dir:
|
||||
|
||||
Returns:
|
||||
None
|
||||
|
||||
"""
|
||||
filename = self.start_time.strftime('%Y-%m-%d %H-%M-%S') + '-remaining.json'
|
||||
output = join(output_dir, filename)
|
||||
self.json_output(output_name=output)
|
||||
@ -0,0 +1,17 @@
|
||||
import logging
|
||||
|
||||
|
||||
def get_logger(name='root'):
|
||||
formatter = logging.Formatter(
|
||||
# fmt='%(asctime)s [%(levelname)s]: %(filename)s(%(funcName)s:%(lineno)s) >> %(message)s')
|
||||
fmt='%(asctime)s [%(levelname)s]: %(message)s', datefmt='%Y-%m-%d %H:%M:%S')
|
||||
|
||||
handler = logging.StreamHandler()
|
||||
handler.setFormatter(formatter)
|
||||
|
||||
logger = logging.getLogger(name)
|
||||
logger.setLevel(logging.INFO)
|
||||
logger.addHandler(handler)
|
||||
return logger
|
||||
|
||||
|
||||
@ -0,0 +1,38 @@
|
||||
import os
|
||||
import yaml
|
||||
from easydict import EasyDict as edict
|
||||
|
||||
class YamlParser(edict):
|
||||
"""
|
||||
This is yaml parser based on EasyDict.
|
||||
"""
|
||||
def __init__(self, cfg_dict=None, config_file=None):
|
||||
if cfg_dict is None:
|
||||
cfg_dict = {}
|
||||
|
||||
if config_file is not None:
|
||||
assert(os.path.isfile(config_file))
|
||||
with open(config_file, 'r') as fo:
|
||||
cfg_dict.update(yaml.load(fo.read()))
|
||||
|
||||
super(YamlParser, self).__init__(cfg_dict)
|
||||
|
||||
|
||||
def merge_from_file(self, config_file):
|
||||
with open(config_file, 'r') as fo:
|
||||
self.update(yaml.load(fo.read(), Loader=yaml.FullLoader))
|
||||
|
||||
|
||||
def merge_from_dict(self, config_dict):
|
||||
self.update(config_dict)
|
||||
|
||||
|
||||
def get_config(config_file=None):
|
||||
return YamlParser(config_file=config_file)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
cfg = YamlParser(config_file="../configs/yolov3.yaml")
|
||||
cfg.merge_from_file("../configs/deep_sort.yaml")
|
||||
|
||||
import ipdb; ipdb.set_trace()
|
||||
@ -0,0 +1,39 @@
|
||||
from functools import wraps
|
||||
from time import time
|
||||
|
||||
|
||||
def is_video(ext: str):
|
||||
"""
|
||||
Returns true if ext exists in
|
||||
allowed_exts for video files.
|
||||
|
||||
Args:
|
||||
ext:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
|
||||
allowed_exts = ('.mp4', '.webm', '.ogg', '.avi', '.wmv', '.mkv', '.3gp')
|
||||
return any((ext.endswith(x) for x in allowed_exts))
|
||||
|
||||
|
||||
def tik_tok(func):
|
||||
"""
|
||||
keep track of time for each process.
|
||||
Args:
|
||||
func:
|
||||
|
||||
Returns:
|
||||
|
||||
"""
|
||||
@wraps(func)
|
||||
def _time_it(*args, **kwargs):
|
||||
start = time()
|
||||
try:
|
||||
return func(*args, **kwargs)
|
||||
finally:
|
||||
end_ = time()
|
||||
print("time: {:.03f}s, fps: {:.03f}".format(end_ - start, 1 / (end_ - start)))
|
||||
|
||||
return _time_it
|
||||
@ -0,0 +1,60 @@
|
||||
from AIDetector_pytorch import Detector
|
||||
import imutils
|
||||
import cv2
|
||||
import os
|
||||
|
||||
def main(video_in):
|
||||
|
||||
name = 'demo'
|
||||
|
||||
det = Detector()
|
||||
cap = cv2.VideoCapture(video_in)
|
||||
fps = int(cap.get(5))
|
||||
print('fps:', fps)
|
||||
t = int(1000/fps)
|
||||
|
||||
videoWriter = None
|
||||
|
||||
while True:
|
||||
|
||||
# try:
|
||||
_, im = cap.read()
|
||||
if im is None:
|
||||
break
|
||||
|
||||
|
||||
x, position = det.detect(im)
|
||||
result = det.feedCap(im)
|
||||
result = result['frame']
|
||||
print(position)
|
||||
result = imutils.resize(result, height=500)
|
||||
if not os.path.exists('runs'):
|
||||
os.mkdir('runs')
|
||||
if videoWriter is None:
|
||||
fourcc = cv2.VideoWriter_fourcc(
|
||||
'm', 'p', '4', 'v') # opencv3.0
|
||||
videoWriter = cv2.VideoWriter(
|
||||
'runs/result.mp4', fourcc, fps, (result.shape[1], result.shape[0]))
|
||||
|
||||
videoWriter.write(result)
|
||||
cv2.imshow(name, result)
|
||||
cv2.waitKey(t)
|
||||
|
||||
if cv2.getWindowProperty(name, cv2.WND_PROP_AUTOSIZE) < 1:
|
||||
# 点x退出
|
||||
break
|
||||
# except Exception as e:
|
||||
# print(e)
|
||||
# break
|
||||
|
||||
cap.release()
|
||||
videoWriter.release()
|
||||
cv2.destroyAllWindows()
|
||||
|
||||
if __name__ == '__main__':
|
||||
import sys
|
||||
try:
|
||||
main(sys.argv[1] if len(sys.argv) > 1 else 0)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
print('Usage: python demo.py [video_path]')
|
||||
|
After Width: | Height: | Size: 799 KiB |
@ -0,0 +1,395 @@
|
||||
# YOLOv5 common modules
|
||||
|
||||
import math
|
||||
from copy import copy
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import requests
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from PIL import Image
|
||||
from torch.cuda import amp
|
||||
|
||||
from utils.datasets import letterbox
|
||||
from utils.general import non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh, save_one_box
|
||||
from utils.plots import colors, plot_one_box
|
||||
from utils.torch_utils import time_synchronized
|
||||
|
||||
|
||||
def autopad(k, p=None): # kernel, padding
|
||||
# Pad to 'same'
|
||||
if p is None:
|
||||
p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
|
||||
return p
|
||||
|
||||
|
||||
def DWConv(c1, c2, k=1, s=1, act=True):
|
||||
# Depthwise convolution
|
||||
return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
|
||||
|
||||
|
||||
class Conv(nn.Module):
|
||||
# Standard convolution
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super(Conv, self).__init__()
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
|
||||
|
||||
def forward(self, x):
|
||||
return self.act(self.bn(self.conv(x)))
|
||||
|
||||
def fuseforward(self, x):
|
||||
return self.act(self.conv(x))
|
||||
|
||||
|
||||
class TransformerLayer(nn.Module):
|
||||
# Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
|
||||
def __init__(self, c, num_heads):
|
||||
super().__init__()
|
||||
self.q = nn.Linear(c, c, bias=False)
|
||||
self.k = nn.Linear(c, c, bias=False)
|
||||
self.v = nn.Linear(c, c, bias=False)
|
||||
self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
|
||||
self.fc1 = nn.Linear(c, c, bias=False)
|
||||
self.fc2 = nn.Linear(c, c, bias=False)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
|
||||
x = self.fc2(self.fc1(x)) + x
|
||||
return x
|
||||
|
||||
|
||||
class TransformerBlock(nn.Module):
|
||||
# Vision Transformer https://arxiv.org/abs/2010.11929
|
||||
def __init__(self, c1, c2, num_heads, num_layers):
|
||||
super().__init__()
|
||||
self.conv = None
|
||||
if c1 != c2:
|
||||
self.conv = Conv(c1, c2)
|
||||
self.linear = nn.Linear(c2, c2) # learnable position embedding
|
||||
self.tr = nn.Sequential(*[TransformerLayer(c2, num_heads) for _ in range(num_layers)])
|
||||
self.c2 = c2
|
||||
|
||||
def forward(self, x):
|
||||
if self.conv is not None:
|
||||
x = self.conv(x)
|
||||
b, _, w, h = x.shape
|
||||
p = x.flatten(2)
|
||||
p = p.unsqueeze(0)
|
||||
p = p.transpose(0, 3)
|
||||
p = p.squeeze(3)
|
||||
e = self.linear(p)
|
||||
x = p + e
|
||||
|
||||
x = self.tr(x)
|
||||
x = x.unsqueeze(3)
|
||||
x = x.transpose(0, 3)
|
||||
x = x.reshape(b, self.c2, w, h)
|
||||
return x
|
||||
|
||||
|
||||
class Bottleneck(nn.Module):
|
||||
# Standard bottleneck
|
||||
def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
|
||||
super(Bottleneck, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_, c2, 3, 1, g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class BottleneckCSP(nn.Module):
|
||||
# CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super(BottleneckCSP, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
|
||||
self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
|
||||
self.cv4 = Conv(2 * c_, c2, 1, 1)
|
||||
self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3)
|
||||
self.act = nn.LeakyReLU(0.1, inplace=True)
|
||||
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
|
||||
|
||||
def forward(self, x):
|
||||
y1 = self.cv3(self.m(self.cv1(x)))
|
||||
y2 = self.cv2(x)
|
||||
return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
|
||||
|
||||
|
||||
class C3(nn.Module):
|
||||
# CSP Bottleneck with 3 convolutions
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
|
||||
super(C3, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c1, c_, 1, 1)
|
||||
self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2)
|
||||
self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
|
||||
# self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
|
||||
|
||||
def forward(self, x):
|
||||
return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
|
||||
|
||||
|
||||
class C3TR(C3):
|
||||
# C3 module with TransformerBlock()
|
||||
def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
|
||||
super().__init__(c1, c2, n, shortcut, g, e)
|
||||
c_ = int(c2 * e)
|
||||
self.m = TransformerBlock(c_, c_, 4, n)
|
||||
|
||||
|
||||
class SPP(nn.Module):
|
||||
# Spatial pyramid pooling layer used in YOLOv3-SPP
|
||||
def __init__(self, c1, c2, k=(5, 9, 13)):
|
||||
super(SPP, self).__init__()
|
||||
c_ = c1 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, 1, 1)
|
||||
self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
|
||||
self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
|
||||
|
||||
def forward(self, x):
|
||||
x = self.cv1(x)
|
||||
return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
|
||||
|
||||
|
||||
class Focus(nn.Module):
|
||||
# Focus wh information into c-space
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super(Focus, self).__init__()
|
||||
self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
|
||||
# self.contract = Contract(gain=2)
|
||||
|
||||
def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
|
||||
return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
|
||||
# return self.conv(self.contract(x))
|
||||
|
||||
|
||||
class Contract(nn.Module):
|
||||
# Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
N, C, H, W = x.size() # assert (H / s == 0) and (W / s == 0), 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(N, C, H // s, s, W // s, s) # x(1,64,40,2,40,2)
|
||||
x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40)
|
||||
return x.view(N, C * s * s, H // s, W // s) # x(1,256,40,40)
|
||||
|
||||
|
||||
class Expand(nn.Module):
|
||||
# Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
|
||||
def __init__(self, gain=2):
|
||||
super().__init__()
|
||||
self.gain = gain
|
||||
|
||||
def forward(self, x):
|
||||
N, C, H, W = x.size() # assert C / s ** 2 == 0, 'Indivisible gain'
|
||||
s = self.gain
|
||||
x = x.view(N, s, s, C // s ** 2, H, W) # x(1,2,2,16,80,80)
|
||||
x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2)
|
||||
return x.view(N, C // s ** 2, H * s, W * s) # x(1,16,160,160)
|
||||
|
||||
|
||||
class Concat(nn.Module):
|
||||
# Concatenate a list of tensors along dimension
|
||||
def __init__(self, dimension=1):
|
||||
super(Concat, self).__init__()
|
||||
self.d = dimension
|
||||
|
||||
def forward(self, x):
|
||||
return torch.cat(x, self.d)
|
||||
|
||||
|
||||
class NMS(nn.Module):
|
||||
# Non-Maximum Suppression (NMS) module
|
||||
conf = 0.25 # confidence threshold
|
||||
iou = 0.45 # IoU threshold
|
||||
classes = None # (optional list) filter by class
|
||||
max_det = 1000 # maximum number of detections per image
|
||||
|
||||
def __init__(self):
|
||||
super(NMS, self).__init__()
|
||||
|
||||
def forward(self, x):
|
||||
return non_max_suppression(x[0], self.conf, iou_thres=self.iou, classes=self.classes, max_det=self.max_det)
|
||||
|
||||
|
||||
class AutoShape(nn.Module):
|
||||
# input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
|
||||
conf = 0.25 # NMS confidence threshold
|
||||
iou = 0.45 # NMS IoU threshold
|
||||
classes = None # (optional list) filter by class
|
||||
max_det = 1000 # maximum number of detections per image
|
||||
|
||||
def __init__(self, model):
|
||||
super(AutoShape, self).__init__()
|
||||
self.model = model.eval()
|
||||
|
||||
def autoshape(self):
|
||||
print('AutoShape already enabled, skipping... ') # model already converted to model.autoshape()
|
||||
return self
|
||||
|
||||
@torch.no_grad()
|
||||
def forward(self, imgs, size=640, augment=False, profile=False):
|
||||
# Inference from various sources. For height=640, width=1280, RGB images example inputs are:
|
||||
# filename: imgs = 'data/images/zidane.jpg'
|
||||
# URI: = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg'
|
||||
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
|
||||
# PIL: = Image.open('image.jpg') # HWC x(640,1280,3)
|
||||
# numpy: = np.zeros((640,1280,3)) # HWC
|
||||
# torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
|
||||
# multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
|
||||
|
||||
t = [time_synchronized()]
|
||||
p = next(self.model.parameters()) # for device and type
|
||||
if isinstance(imgs, torch.Tensor): # torch
|
||||
with amp.autocast(enabled=p.device.type != 'cpu'):
|
||||
return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
|
||||
|
||||
# Pre-process
|
||||
n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs]) # number of images, list of images
|
||||
shape0, shape1, files = [], [], [] # image and inference shapes, filenames
|
||||
for i, im in enumerate(imgs):
|
||||
f = f'image{i}' # filename
|
||||
if isinstance(im, str): # filename or uri
|
||||
im, f = np.asarray(Image.open(requests.get(im, stream=True).raw if im.startswith('http') else im)), im
|
||||
elif isinstance(im, Image.Image): # PIL Image
|
||||
im, f = np.asarray(im), getattr(im, 'filename', f) or f
|
||||
files.append(Path(f).with_suffix('.jpg').name)
|
||||
if im.shape[0] < 5: # image in CHW
|
||||
im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
|
||||
im = im[:, :, :3] if im.ndim == 3 else np.tile(im[:, :, None], 3) # enforce 3ch input
|
||||
s = im.shape[:2] # HWC
|
||||
shape0.append(s) # image shape
|
||||
g = (size / max(s)) # gain
|
||||
shape1.append([y * g for y in s])
|
||||
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
|
||||
shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)] # inference shape
|
||||
x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs] # pad
|
||||
x = np.stack(x, 0) if n > 1 else x[0][None] # stack
|
||||
x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
|
||||
x = torch.from_numpy(x).to(p.device).type_as(p) / 255. # uint8 to fp16/32
|
||||
t.append(time_synchronized())
|
||||
|
||||
with amp.autocast(enabled=p.device.type != 'cpu'):
|
||||
# Inference
|
||||
y = self.model(x, augment, profile)[0] # forward
|
||||
t.append(time_synchronized())
|
||||
|
||||
# Post-process
|
||||
y = non_max_suppression(y, self.conf, iou_thres=self.iou, classes=self.classes, max_det=self.max_det) # NMS
|
||||
for i in range(n):
|
||||
scale_coords(shape1, y[i][:, :4], shape0[i])
|
||||
|
||||
t.append(time_synchronized())
|
||||
return Detections(imgs, y, files, t, self.names, x.shape)
|
||||
|
||||
|
||||
class Detections:
|
||||
# detections class for YOLOv5 inference results
|
||||
def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
|
||||
super(Detections, self).__init__()
|
||||
d = pred[0].device # device
|
||||
gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs] # normalizations
|
||||
self.imgs = imgs # list of images as numpy arrays
|
||||
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
|
||||
self.names = names # class names
|
||||
self.files = files # image filenames
|
||||
self.xyxy = pred # xyxy pixels
|
||||
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
|
||||
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
|
||||
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
|
||||
self.n = len(self.pred) # number of images (batch size)
|
||||
self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
|
||||
self.s = shape # inference BCHW shape
|
||||
|
||||
def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
|
||||
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
|
||||
str = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '
|
||||
if pred is not None:
|
||||
for c in pred[:, -1].unique():
|
||||
n = (pred[:, -1] == c).sum() # detections per class
|
||||
str += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
|
||||
if show or save or render or crop:
|
||||
for *box, conf, cls in pred: # xyxy, confidence, class
|
||||
label = f'{self.names[int(cls)]} {conf:.2f}'
|
||||
if crop:
|
||||
save_one_box(box, im, file=save_dir / 'crops' / self.names[int(cls)] / self.files[i])
|
||||
else: # all others
|
||||
plot_one_box(box, im, label=label, color=colors(cls))
|
||||
|
||||
im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
|
||||
if pprint:
|
||||
print(str.rstrip(', '))
|
||||
if show:
|
||||
im.show(self.files[i]) # show
|
||||
if save:
|
||||
f = self.files[i]
|
||||
im.save(save_dir / f) # save
|
||||
print(f"{'Saved' * (i == 0)} {f}", end=',' if i < self.n - 1 else f' to {save_dir}\n')
|
||||
if render:
|
||||
self.imgs[i] = np.asarray(im)
|
||||
|
||||
def print(self):
|
||||
self.display(pprint=True) # print results
|
||||
print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' % self.t)
|
||||
|
||||
def show(self):
|
||||
self.display(show=True) # show results
|
||||
|
||||
def save(self, save_dir='runs/hub/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/hub/exp', mkdir=True) # increment save_dir
|
||||
self.display(save=True, save_dir=save_dir) # save results
|
||||
|
||||
def crop(self, save_dir='runs/hub/exp'):
|
||||
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/hub/exp', mkdir=True) # increment save_dir
|
||||
self.display(crop=True, save_dir=save_dir) # crop results
|
||||
print(f'Saved results to {save_dir}\n')
|
||||
|
||||
def render(self):
|
||||
self.display(render=True) # render results
|
||||
return self.imgs
|
||||
|
||||
def pandas(self):
|
||||
# return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
|
||||
new = copy(self) # return copy
|
||||
ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
|
||||
cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
|
||||
for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
|
||||
a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
|
||||
setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
|
||||
return new
|
||||
|
||||
def tolist(self):
|
||||
# return a list of Detections objects, i.e. 'for result in results.tolist():'
|
||||
x = [Detections([self.imgs[i]], [self.pred[i]], self.names, self.s) for i in range(self.n)]
|
||||
for d in x:
|
||||
for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
|
||||
setattr(d, k, getattr(d, k)[0]) # pop out of list
|
||||
return x
|
||||
|
||||
def __len__(self):
|
||||
return self.n
|
||||
|
||||
|
||||
class Classify(nn.Module):
|
||||
# Classification head, i.e. x(b,c1,20,20) to x(b,c2)
|
||||
def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups
|
||||
super(Classify, self).__init__()
|
||||
self.aap = nn.AdaptiveAvgPool2d(1) # to x(b,c1,1,1)
|
||||
self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g) # to x(b,c2,1,1)
|
||||
self.flat = nn.Flatten()
|
||||
|
||||
def forward(self, x):
|
||||
z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1) # cat if list
|
||||
return self.flat(self.conv(z)) # flatten to x(b,c2)
|
||||
@ -0,0 +1,137 @@
|
||||
# YOLOv5 experimental modules
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from models.common import Conv, DWConv
|
||||
from utils.google_utils import attempt_download
|
||||
|
||||
|
||||
class CrossConv(nn.Module):
|
||||
# Cross Convolution Downsample
|
||||
def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
|
||||
# ch_in, ch_out, kernel, stride, groups, expansion, shortcut
|
||||
super(CrossConv, self).__init__()
|
||||
c_ = int(c2 * e) # hidden channels
|
||||
self.cv1 = Conv(c1, c_, (1, k), (1, s))
|
||||
self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
|
||||
self.add = shortcut and c1 == c2
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
|
||||
|
||||
|
||||
class Sum(nn.Module):
|
||||
# Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
|
||||
def __init__(self, n, weight=False): # n: number of inputs
|
||||
super(Sum, self).__init__()
|
||||
self.weight = weight # apply weights boolean
|
||||
self.iter = range(n - 1) # iter object
|
||||
if weight:
|
||||
self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True) # layer weights
|
||||
|
||||
def forward(self, x):
|
||||
y = x[0] # no weight
|
||||
if self.weight:
|
||||
w = torch.sigmoid(self.w) * 2
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1] * w[i]
|
||||
else:
|
||||
for i in self.iter:
|
||||
y = y + x[i + 1]
|
||||
return y
|
||||
|
||||
|
||||
class GhostConv(nn.Module):
|
||||
# Ghost Convolution https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
|
||||
super(GhostConv, self).__init__()
|
||||
c_ = c2 // 2 # hidden channels
|
||||
self.cv1 = Conv(c1, c_, k, s, None, g, act)
|
||||
self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
|
||||
|
||||
def forward(self, x):
|
||||
y = self.cv1(x)
|
||||
return torch.cat([y, self.cv2(y)], 1)
|
||||
|
||||
|
||||
class GhostBottleneck(nn.Module):
|
||||
# Ghost Bottleneck https://github.com/huawei-noah/ghostnet
|
||||
def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
|
||||
super(GhostBottleneck, self).__init__()
|
||||
c_ = c2 // 2
|
||||
self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1), # pw
|
||||
DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
|
||||
GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
|
||||
self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
|
||||
Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
|
||||
|
||||
def forward(self, x):
|
||||
return self.conv(x) + self.shortcut(x)
|
||||
|
||||
|
||||
class MixConv2d(nn.Module):
|
||||
# Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
|
||||
def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
|
||||
super(MixConv2d, self).__init__()
|
||||
groups = len(k)
|
||||
if equal_ch: # equal c_ per group
|
||||
i = torch.linspace(0, groups - 1E-6, c2).floor() # c2 indices
|
||||
c_ = [(i == g).sum() for g in range(groups)] # intermediate channels
|
||||
else: # equal weight.numel() per group
|
||||
b = [c2] + [0] * groups
|
||||
a = np.eye(groups + 1, groups, k=-1)
|
||||
a -= np.roll(a, 1, axis=1)
|
||||
a *= np.array(k) ** 2
|
||||
a[0] = 1
|
||||
c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
|
||||
|
||||
self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
|
||||
self.bn = nn.BatchNorm2d(c2)
|
||||
self.act = nn.LeakyReLU(0.1, inplace=True)
|
||||
|
||||
def forward(self, x):
|
||||
return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
|
||||
|
||||
|
||||
class Ensemble(nn.ModuleList):
|
||||
# Ensemble of models
|
||||
def __init__(self):
|
||||
super(Ensemble, self).__init__()
|
||||
|
||||
def forward(self, x, augment=False):
|
||||
y = []
|
||||
for module in self:
|
||||
y.append(module(x, augment)[0])
|
||||
# y = torch.stack(y).max(0)[0] # max ensemble
|
||||
# y = torch.stack(y).mean(0) # mean ensemble
|
||||
y = torch.cat(y, 1) # nms ensemble
|
||||
return y, None # inference, train output
|
||||
|
||||
|
||||
def attempt_load(weights, map_location=None, inplace=True):
|
||||
from models.yolo import Detect, Model
|
||||
|
||||
# Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
|
||||
model = Ensemble()
|
||||
for w in weights if isinstance(weights, list) else [weights]:
|
||||
attempt_download(w)
|
||||
ckpt = torch.load(w, map_location=map_location) # load
|
||||
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
|
||||
|
||||
# Compatibility updates
|
||||
for m in model.modules():
|
||||
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
|
||||
m.inplace = inplace # pytorch 1.7.0 compatibility
|
||||
elif type(m) is Conv:
|
||||
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
|
||||
|
||||
if len(model) == 1:
|
||||
return model[-1] # return model
|
||||
else:
|
||||
print(f'Ensemble created with {weights}\n')
|
||||
for k in ['names']:
|
||||
setattr(model, k, getattr(model[-1], k))
|
||||
model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride
|
||||
return model # return ensemble
|
||||
@ -0,0 +1,143 @@
|
||||
"""Exports a YOLOv5 *.pt model to TorchScript, ONNX, CoreML formats
|
||||
|
||||
Usage:
|
||||
$ python path/to/models/export.py --weights yolov5s.pt --img 640 --batch 1
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.append(Path(__file__).parent.parent.absolute().__str__()) # to run '$ python *.py' files in subdirectories
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
from torch.utils.mobile_optimizer import optimize_for_mobile
|
||||
|
||||
import models
|
||||
from models.experimental import attempt_load
|
||||
from utils.activations import Hardswish, SiLU
|
||||
from utils.general import colorstr, check_img_size, check_requirements, file_size, set_logging
|
||||
from utils.torch_utils import select_device
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path')
|
||||
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width
|
||||
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
|
||||
parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats')
|
||||
parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
|
||||
parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
|
||||
parser.add_argument('--train', action='store_true', help='model.train() mode')
|
||||
parser.add_argument('--optimize', action='store_true', help='optimize TorchScript for mobile') # TorchScript-only
|
||||
parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes') # ONNX-only
|
||||
parser.add_argument('--simplify', action='store_true', help='simplify ONNX model') # ONNX-only
|
||||
parser.add_argument('--opset-version', type=int, default=12, help='ONNX opset version') # ONNX-only
|
||||
opt = parser.parse_args()
|
||||
opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand
|
||||
opt.include = [x.lower() for x in opt.include]
|
||||
print(opt)
|
||||
set_logging()
|
||||
t = time.time()
|
||||
|
||||
# Load PyTorch model
|
||||
device = select_device(opt.device)
|
||||
model = attempt_load(opt.weights, map_location=device) # load FP32 model
|
||||
labels = model.names
|
||||
|
||||
# Checks
|
||||
gs = int(max(model.stride)) # grid size (max stride)
|
||||
opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples
|
||||
assert not (opt.device.lower() == 'cpu' and opt.half), '--half only compatible with GPU export, i.e. use --device 0'
|
||||
|
||||
# Input
|
||||
img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection
|
||||
|
||||
# Update model
|
||||
if opt.half:
|
||||
img, model = img.half(), model.half() # to FP16
|
||||
if opt.train:
|
||||
model.train() # training mode (no grid construction in Detect layer)
|
||||
for k, m in model.named_modules():
|
||||
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
|
||||
if isinstance(m, models.common.Conv): # assign export-friendly activations
|
||||
if isinstance(m.act, nn.Hardswish):
|
||||
m.act = Hardswish()
|
||||
elif isinstance(m.act, nn.SiLU):
|
||||
m.act = SiLU()
|
||||
elif isinstance(m, models.yolo.Detect):
|
||||
m.inplace = opt.inplace
|
||||
m.onnx_dynamic = opt.dynamic
|
||||
# m.forward = m.forward_export # assign forward (optional)
|
||||
|
||||
for _ in range(2):
|
||||
y = model(img) # dry runs
|
||||
print(f"\n{colorstr('PyTorch:')} starting from {opt.weights} ({file_size(opt.weights):.1f} MB)")
|
||||
|
||||
# TorchScript export -----------------------------------------------------------------------------------------------
|
||||
if 'torchscript' in opt.include or 'coreml' in opt.include:
|
||||
prefix = colorstr('TorchScript:')
|
||||
try:
|
||||
print(f'\n{prefix} starting export with torch {torch.__version__}...')
|
||||
f = opt.weights.replace('.pt', '.torchscript.pt') # filename
|
||||
ts = torch.jit.trace(model, img, strict=False)
|
||||
(optimize_for_mobile(ts) if opt.optimize else ts).save(f)
|
||||
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
print(f'{prefix} export failure: {e}')
|
||||
|
||||
# ONNX export ------------------------------------------------------------------------------------------------------
|
||||
if 'onnx' in opt.include:
|
||||
prefix = colorstr('ONNX:')
|
||||
try:
|
||||
import onnx
|
||||
|
||||
print(f'{prefix} starting export with onnx {onnx.__version__}...')
|
||||
f = opt.weights.replace('.pt', '.onnx') # filename
|
||||
torch.onnx.export(model, img, f, verbose=False, opset_version=opt.opset_version, input_names=['images'],
|
||||
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # size(1,3,640,640)
|
||||
'output': {0: 'batch', 2: 'y', 3: 'x'}} if opt.dynamic else None)
|
||||
|
||||
# Checks
|
||||
model_onnx = onnx.load(f) # load onnx model
|
||||
onnx.checker.check_model(model_onnx) # check onnx model
|
||||
# print(onnx.helper.printable_graph(model_onnx.graph)) # print
|
||||
|
||||
# Simplify
|
||||
if opt.simplify:
|
||||
try:
|
||||
check_requirements(['onnx-simplifier'])
|
||||
import onnxsim
|
||||
|
||||
print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
|
||||
model_onnx, check = onnxsim.simplify(
|
||||
model_onnx,
|
||||
dynamic_input_shape=opt.dynamic,
|
||||
input_shapes={'images': list(img.shape)} if opt.dynamic else None)
|
||||
assert check, 'assert check failed'
|
||||
onnx.save(model_onnx, f)
|
||||
except Exception as e:
|
||||
print(f'{prefix} simplifier failure: {e}')
|
||||
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
print(f'{prefix} export failure: {e}')
|
||||
|
||||
# CoreML export ----------------------------------------------------------------------------------------------------
|
||||
if 'coreml' in opt.include:
|
||||
prefix = colorstr('CoreML:')
|
||||
try:
|
||||
import coremltools as ct
|
||||
|
||||
print(f'{prefix} starting export with coremltools {ct.__version__}...')
|
||||
assert opt.train, 'CoreML exports should be placed in model.train() mode with `python export.py --train`'
|
||||
model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
|
||||
f = opt.weights.replace('.pt', '.mlmodel') # filename
|
||||
model.save(f)
|
||||
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
|
||||
except Exception as e:
|
||||
print(f'{prefix} export failure: {e}')
|
||||
|
||||
# Finish
|
||||
print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.')
|
||||
@ -0,0 +1,58 @@
|
||||
# Default YOLOv5 anchors for COCO data
|
||||
|
||||
|
||||
# P5 -------------------------------------------------------------------------------------------------------------------
|
||||
# P5-640:
|
||||
anchors_p5_640:
|
||||
- [ 10,13, 16,30, 33,23 ] # P3/8
|
||||
- [ 30,61, 62,45, 59,119 ] # P4/16
|
||||
- [ 116,90, 156,198, 373,326 ] # P5/32
|
||||
|
||||
|
||||
# P6 -------------------------------------------------------------------------------------------------------------------
|
||||
# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
|
||||
anchors_p6_640:
|
||||
- [ 9,11, 21,19, 17,41 ] # P3/8
|
||||
- [ 43,32, 39,70, 86,64 ] # P4/16
|
||||
- [ 65,131, 134,130, 120,265 ] # P5/32
|
||||
- [ 282,180, 247,354, 512,387 ] # P6/64
|
||||
|
||||
# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792
|
||||
anchors_p6_1280:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187
|
||||
anchors_p6_1920:
|
||||
- [ 28,41, 67,59, 57,141 ] # P3/8
|
||||
- [ 144,103, 129,227, 270,205 ] # P4/16
|
||||
- [ 209,452, 455,396, 358,812 ] # P5/32
|
||||
- [ 653,922, 1109,570, 1387,1187 ] # P6/64
|
||||
|
||||
|
||||
# P7 -------------------------------------------------------------------------------------------------------------------
|
||||
# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372
|
||||
anchors_p7_640:
|
||||
- [ 11,11, 13,30, 29,20 ] # P3/8
|
||||
- [ 30,46, 61,38, 39,92 ] # P4/16
|
||||
- [ 78,80, 146,66, 79,163 ] # P5/32
|
||||
- [ 149,150, 321,143, 157,303 ] # P6/64
|
||||
- [ 257,402, 359,290, 524,372 ] # P7/128
|
||||
|
||||
# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818
|
||||
anchors_p7_1280:
|
||||
- [ 19,22, 54,36, 32,77 ] # P3/8
|
||||
- [ 70,83, 138,71, 75,173 ] # P4/16
|
||||
- [ 165,159, 148,334, 375,151 ] # P5/32
|
||||
- [ 334,317, 251,626, 499,474 ] # P6/64
|
||||
- [ 750,326, 534,814, 1079,818 ] # P7/128
|
||||
|
||||
# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227
|
||||
anchors_p7_1920:
|
||||
- [ 29,34, 81,55, 47,115 ] # P3/8
|
||||
- [ 105,124, 207,107, 113,259 ] # P4/16
|
||||
- [ 247,238, 222,500, 563,227 ] # P5/32
|
||||
- [ 501,476, 376,939, 749,711 ] # P6/64
|
||||
- [ 1126,489, 801,1222, 1618,1227 ] # P7/128
|
||||
@ -0,0 +1,51 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3-SPP head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, SPP, [512, [5, 9, 13]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,41 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,14, 23,27, 37,58] # P4/16
|
||||
- [81,82, 135,169, 344,319] # P5/32
|
||||
|
||||
# YOLOv3-tiny backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [16, 3, 1]], # 0
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2
|
||||
[-1, 1, Conv, [32, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4
|
||||
[-1, 1, Conv, [64, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8
|
||||
[-1, 1, Conv, [128, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16
|
||||
[-1, 1, Conv, [256, 3, 1]],
|
||||
[-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32
|
||||
[-1, 1, Conv, [512, 3, 1]],
|
||||
[-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11
|
||||
[-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12
|
||||
]
|
||||
|
||||
# YOLOv3-tiny head
|
||||
head:
|
||||
[[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium)
|
||||
|
||||
[[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5)
|
||||
]
|
||||
@ -0,0 +1,51 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# darknet53 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Conv, [32, 3, 1]], # 0
|
||||
[-1, 1, Conv, [64, 3, 2]], # 1-P1/2
|
||||
[-1, 1, Bottleneck, [64]],
|
||||
[-1, 1, Conv, [128, 3, 2]], # 3-P2/4
|
||||
[-1, 2, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 5-P3/8
|
||||
[-1, 8, Bottleneck, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 7-P4/16
|
||||
[-1, 8, Bottleneck, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
|
||||
[-1, 4, Bottleneck, [1024]], # 10
|
||||
]
|
||||
|
||||
# YOLOv3 head
|
||||
head:
|
||||
[[-1, 1, Bottleneck, [1024, False]],
|
||||
[-1, 1, Conv, [512, [1, 1]]],
|
||||
[-1, 1, Conv, [1024, 3, 1]],
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
|
||||
|
||||
[-2, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 8], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Bottleneck, [512, False]],
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
|
||||
|
||||
[-2, 1, Conv, [128, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Bottleneck, [256, False]],
|
||||
[-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
|
||||
|
||||
[[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,42 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, Bottleneck, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 6, BottleneckCSP, [1024]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 FPN head
|
||||
head:
|
||||
[[-1, 3, BottleneckCSP, [1024, False]], # 10 (P5/32-large)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 14 (P4/16-medium)
|
||||
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 3, BottleneckCSP, [256, False]], # 18 (P3/8-small)
|
||||
|
||||
[[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,54 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 1, SPP, [ 1024, [ 5, 9, 13 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 13
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 17 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 128, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 2 ], 1, Concat, [ 1 ] ], # cat backbone P2
|
||||
[ -1, 1, C3, [ 128, False ] ], # 21 (P2/4-xsmall)
|
||||
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ],
|
||||
[ [ -1, 18 ], 1, Concat, [ 1 ] ], # cat head P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 24 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 27 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 10 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 30 (P5/32-large)
|
||||
|
||||
[ [ 24, 27, 30 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,56 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 15
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 19
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 32 (P5/64-xlarge)
|
||||
|
||||
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,67 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors: 3
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 3, C3, [ 1024 ] ],
|
||||
[ -1, 1, Conv, [ 1280, 3, 2 ] ], # 11-P7/128
|
||||
[ -1, 1, SPP, [ 1280, [ 3, 5 ] ] ],
|
||||
[ -1, 3, C3, [ 1280, False ] ], # 13
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 1024, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 10 ], 1, Concat, [ 1 ] ], # cat backbone P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 17
|
||||
|
||||
[ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 21
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 25
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 29 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 26 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 32 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 22 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 35 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 18 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 38 (P6/64-xlarge)
|
||||
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ],
|
||||
[ [ -1, 14 ], 1, Concat, [ 1 ] ], # cat head P7
|
||||
[ -1, 3, C3, [ 1280, False ] ], # 41 (P7/128-xxlarge)
|
||||
|
||||
[ [ 29, 32, 35, 38, 41 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6, P7)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, BottleneckCSP, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, BottleneckCSP, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, BottleneckCSP, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 PANet head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, BottleneckCSP, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 15
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 19
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
|
||||
|
||||
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 15
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 19
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
|
||||
|
||||
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3TR, [1024, False]], # 9 <-------- C3TR() Transformer module
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 15
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 19
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
|
||||
|
||||
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,60 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [ 19,27, 44,40, 38,94 ] # P3/8
|
||||
- [ 96,68, 86,152, 180,137 ] # P4/16
|
||||
- [ 140,301, 303,264, 238,542 ] # P5/32
|
||||
- [ 436,615, 739,380, 925,792 ] # P6/64
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[ [ -1, 1, Focus, [ 64, 3 ] ], # 0-P1/2
|
||||
[ -1, 1, Conv, [ 128, 3, 2 ] ], # 1-P2/4
|
||||
[ -1, 3, C3, [ 128 ] ],
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ], # 3-P3/8
|
||||
[ -1, 9, C3, [ 256 ] ],
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ], # 5-P4/16
|
||||
[ -1, 9, C3, [ 512 ] ],
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ], # 7-P5/32
|
||||
[ -1, 3, C3, [ 768 ] ],
|
||||
[ -1, 1, Conv, [ 1024, 3, 2 ] ], # 9-P6/64
|
||||
[ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 11
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[ [ -1, 1, Conv, [ 768, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 8 ], 1, Concat, [ 1 ] ], # cat backbone P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 15
|
||||
|
||||
[ -1, 1, Conv, [ 512, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 6 ], 1, Concat, [ 1 ] ], # cat backbone P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 19
|
||||
|
||||
[ -1, 1, Conv, [ 256, 1, 1 ] ],
|
||||
[ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
|
||||
[ [ -1, 4 ], 1, Concat, [ 1 ] ], # cat backbone P3
|
||||
[ -1, 3, C3, [ 256, False ] ], # 23 (P3/8-small)
|
||||
|
||||
[ -1, 1, Conv, [ 256, 3, 2 ] ],
|
||||
[ [ -1, 20 ], 1, Concat, [ 1 ] ], # cat head P4
|
||||
[ -1, 3, C3, [ 512, False ] ], # 26 (P4/16-medium)
|
||||
|
||||
[ -1, 1, Conv, [ 512, 3, 2 ] ],
|
||||
[ [ -1, 16 ], 1, Concat, [ 1 ] ], # cat head P5
|
||||
[ -1, 3, C3, [ 768, False ] ], # 29 (P5/32-large)
|
||||
|
||||
[ -1, 1, Conv, [ 768, 3, 2 ] ],
|
||||
[ [ -1, 12 ], 1, Concat, [ 1 ] ], # cat head P6
|
||||
[ -1, 3, C3, [ 1024, False ] ], # 32 (P6/64-xlarge)
|
||||
|
||||
[ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ], # Detect(P3, P4, P5, P6)
|
||||
]
|
||||
@ -0,0 +1,304 @@
|
||||
# YOLOv5 YOLO-specific modules
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import sys
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.append(Path(__file__).parent.parent.absolute().__str__()) # to run '$ python *.py' files in subdirectories
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
from models.common import *
|
||||
from models.experimental import *
|
||||
from utils.autoanchor import check_anchor_order
|
||||
from utils.general import make_divisible, check_file, set_logging
|
||||
from utils.torch_utils import time_synchronized, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
|
||||
select_device, copy_attr
|
||||
|
||||
try:
|
||||
import thop # for FLOPS computation
|
||||
except ImportError:
|
||||
thop = None
|
||||
|
||||
|
||||
class Detect(nn.Module):
|
||||
stride = None # strides computed during build
|
||||
onnx_dynamic = False # ONNX export parameter
|
||||
|
||||
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
|
||||
super(Detect, self).__init__()
|
||||
self.nc = nc # number of classes
|
||||
self.no = nc + 5 # number of outputs per anchor
|
||||
self.nl = len(anchors) # number of detection layers
|
||||
self.na = len(anchors[0]) // 2 # number of anchors
|
||||
self.grid = [torch.zeros(1)] * self.nl # init grid
|
||||
a = torch.tensor(anchors).float().view(self.nl, -1, 2)
|
||||
self.register_buffer('anchors', a) # shape(nl,na,2)
|
||||
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
|
||||
self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
|
||||
self.inplace = inplace # use in-place ops (e.g. slice assignment)
|
||||
|
||||
def forward(self, x):
|
||||
# x = x.copy() # for profiling
|
||||
z = [] # inference output
|
||||
for i in range(self.nl):
|
||||
x[i] = self.m[i](x[i]) # conv
|
||||
bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
|
||||
x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
|
||||
|
||||
if not self.training: # inference
|
||||
if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
|
||||
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
|
||||
|
||||
y = x[i].sigmoid()
|
||||
if self.inplace:
|
||||
y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
|
||||
else: # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
|
||||
xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i] # xy
|
||||
wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2) # wh
|
||||
y = torch.cat((xy, wh, y[..., 4:]), -1)
|
||||
z.append(y.view(bs, -1, self.no))
|
||||
|
||||
return x if self.training else (torch.cat(z, 1), x)
|
||||
|
||||
@staticmethod
|
||||
def _make_grid(nx=20, ny=20):
|
||||
yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
|
||||
return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
|
||||
|
||||
|
||||
class Model(nn.Module):
|
||||
def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
|
||||
super(Model, self).__init__()
|
||||
if isinstance(cfg, dict):
|
||||
self.yaml = cfg # model dict
|
||||
else: # is *.yaml
|
||||
import yaml # for torch hub
|
||||
self.yaml_file = Path(cfg).name
|
||||
with open(cfg) as f:
|
||||
self.yaml = yaml.safe_load(f) # model dict
|
||||
|
||||
# Define model
|
||||
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
|
||||
if nc and nc != self.yaml['nc']:
|
||||
logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
|
||||
self.yaml['nc'] = nc # override yaml value
|
||||
if anchors:
|
||||
logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
|
||||
self.yaml['anchors'] = round(anchors) # override yaml value
|
||||
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
|
||||
self.names = [str(i) for i in range(self.yaml['nc'])] # default names
|
||||
self.inplace = self.yaml.get('inplace', True)
|
||||
# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
|
||||
|
||||
# Build strides, anchors
|
||||
m = self.model[-1] # Detect()
|
||||
if isinstance(m, Detect):
|
||||
s = 256 # 2x min stride
|
||||
m.inplace = self.inplace
|
||||
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
|
||||
m.anchors /= m.stride.view(-1, 1, 1)
|
||||
check_anchor_order(m)
|
||||
self.stride = m.stride
|
||||
self._initialize_biases() # only run once
|
||||
# logger.info('Strides: %s' % m.stride.tolist())
|
||||
|
||||
# Init weights, biases
|
||||
initialize_weights(self)
|
||||
self.info()
|
||||
logger.info('')
|
||||
|
||||
def forward(self, x, augment=False, profile=False):
|
||||
if augment:
|
||||
return self.forward_augment(x) # augmented inference, None
|
||||
else:
|
||||
return self.forward_once(x, profile) # single-scale inference, train
|
||||
|
||||
def forward_augment(self, x):
|
||||
img_size = x.shape[-2:] # height, width
|
||||
s = [1, 0.83, 0.67] # scales
|
||||
f = [None, 3, None] # flips (2-ud, 3-lr)
|
||||
y = [] # outputs
|
||||
for si, fi in zip(s, f):
|
||||
xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
|
||||
yi = self.forward_once(xi)[0] # forward
|
||||
# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
|
||||
yi = self._descale_pred(yi, fi, si, img_size)
|
||||
y.append(yi)
|
||||
return torch.cat(y, 1), None # augmented inference, train
|
||||
|
||||
def forward_once(self, x, profile=False):
|
||||
y, dt = [], [] # outputs
|
||||
for m in self.model:
|
||||
if m.f != -1: # if not from previous layer
|
||||
x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
|
||||
|
||||
if profile:
|
||||
o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPS
|
||||
t = time_synchronized()
|
||||
for _ in range(10):
|
||||
_ = m(x)
|
||||
dt.append((time_synchronized() - t) * 100)
|
||||
if m == self.model[0]:
|
||||
logger.info(f"{'time (ms)':>10s} {'GFLOPS':>10s} {'params':>10s} {'module'}")
|
||||
logger.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
|
||||
|
||||
x = m(x) # run
|
||||
y.append(x if m.i in self.save else None) # save output
|
||||
|
||||
if profile:
|
||||
logger.info('%.1fms total' % sum(dt))
|
||||
return x
|
||||
|
||||
def _descale_pred(self, p, flips, scale, img_size):
|
||||
# de-scale predictions following augmented inference (inverse operation)
|
||||
if self.inplace:
|
||||
p[..., :4] /= scale # de-scale
|
||||
if flips == 2:
|
||||
p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
|
||||
elif flips == 3:
|
||||
p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
|
||||
else:
|
||||
x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
|
||||
if flips == 2:
|
||||
y = img_size[0] - y # de-flip ud
|
||||
elif flips == 3:
|
||||
x = img_size[1] - x # de-flip lr
|
||||
p = torch.cat((x, y, wh, p[..., 4:]), -1)
|
||||
return p
|
||||
|
||||
def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
|
||||
# https://arxiv.org/abs/1708.02002 section 3.3
|
||||
# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi, s in zip(m.m, m.stride): # from
|
||||
b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
|
||||
b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
|
||||
b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum()) # cls
|
||||
mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
|
||||
|
||||
def _print_biases(self):
|
||||
m = self.model[-1] # Detect() module
|
||||
for mi in m.m: # from
|
||||
b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
|
||||
logger.info(
|
||||
('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
|
||||
|
||||
# def _print_weights(self):
|
||||
# for m in self.model.modules():
|
||||
# if type(m) is Bottleneck:
|
||||
# logger.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
|
||||
|
||||
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
|
||||
logger.info('Fusing layers... ')
|
||||
for m in self.model.modules():
|
||||
if type(m) is Conv and hasattr(m, 'bn'):
|
||||
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
|
||||
delattr(m, 'bn') # remove batchnorm
|
||||
m.forward = m.fuseforward # update forward
|
||||
self.info()
|
||||
return self
|
||||
|
||||
def nms(self, mode=True): # add or remove NMS module
|
||||
present = type(self.model[-1]) is NMS # last layer is NMS
|
||||
if mode and not present:
|
||||
logger.info('Adding NMS... ')
|
||||
m = NMS() # module
|
||||
m.f = -1 # from
|
||||
m.i = self.model[-1].i + 1 # index
|
||||
self.model.add_module(name='%s' % m.i, module=m) # add
|
||||
self.eval()
|
||||
elif not mode and present:
|
||||
logger.info('Removing NMS... ')
|
||||
self.model = self.model[:-1] # remove
|
||||
return self
|
||||
|
||||
def autoshape(self): # add AutoShape module
|
||||
logger.info('Adding AutoShape... ')
|
||||
m = AutoShape(self) # wrap model
|
||||
copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
|
||||
return m
|
||||
|
||||
def info(self, verbose=False, img_size=640): # print model information
|
||||
model_info(self, verbose, img_size)
|
||||
|
||||
|
||||
def parse_model(d, ch): # model_dict, input_channels(3)
|
||||
logger.info('\n%3s%18s%3s%10s %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
|
||||
anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
|
||||
na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
|
||||
no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
|
||||
|
||||
layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
|
||||
for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
|
||||
m = eval(m) if isinstance(m, str) else m # eval strings
|
||||
for j, a in enumerate(args):
|
||||
try:
|
||||
args[j] = eval(a) if isinstance(a, str) else a # eval strings
|
||||
except:
|
||||
pass
|
||||
|
||||
n = max(round(n * gd), 1) if n > 1 else n # depth gain
|
||||
if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,
|
||||
C3, C3TR]:
|
||||
c1, c2 = ch[f], args[0]
|
||||
if c2 != no: # if not output
|
||||
c2 = make_divisible(c2 * gw, 8)
|
||||
|
||||
args = [c1, c2, *args[1:]]
|
||||
if m in [BottleneckCSP, C3, C3TR]:
|
||||
args.insert(2, n) # number of repeats
|
||||
n = 1
|
||||
elif m is nn.BatchNorm2d:
|
||||
args = [ch[f]]
|
||||
elif m is Concat:
|
||||
c2 = sum([ch[x] for x in f])
|
||||
elif m is Detect:
|
||||
args.append([ch[x] for x in f])
|
||||
if isinstance(args[1], int): # number of anchors
|
||||
args[1] = [list(range(args[1] * 2))] * len(f)
|
||||
elif m is Contract:
|
||||
c2 = ch[f] * args[0] ** 2
|
||||
elif m is Expand:
|
||||
c2 = ch[f] // args[0] ** 2
|
||||
else:
|
||||
c2 = ch[f]
|
||||
|
||||
m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module
|
||||
t = str(m)[8:-2].replace('__main__.', '') # module type
|
||||
np = sum([x.numel() for x in m_.parameters()]) # number params
|
||||
m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
|
||||
logger.info('%3s%18s%3s%10.0f %-40s%-30s' % (i, f, n, np, t, args)) # print
|
||||
save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
|
||||
layers.append(m_)
|
||||
if i == 0:
|
||||
ch = []
|
||||
ch.append(c2)
|
||||
return nn.Sequential(*layers), sorted(save)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
|
||||
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
||||
opt = parser.parse_args()
|
||||
opt.cfg = check_file(opt.cfg) # check file
|
||||
set_logging()
|
||||
device = select_device(opt.device)
|
||||
|
||||
# Create model
|
||||
model = Model(opt.cfg).to(device)
|
||||
model.train()
|
||||
|
||||
# Profile
|
||||
# img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 320, 320).to(device)
|
||||
# y = model(img, profile=True)
|
||||
|
||||
# Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
|
||||
# from torch.utils.tensorboard import SummaryWriter
|
||||
# tb_writer = SummaryWriter('.')
|
||||
# logger.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
|
||||
# tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph
|
||||
# tb_writer.add_image('test', img[0], dataformats='CWH') # add model to tensorboard
|
||||
@ -0,0 +1,48 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.0 # model depth multiple
|
||||
width_multiple: 1.0 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.67 # model depth multiple
|
||||
width_multiple: 0.75 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 0.33 # model depth multiple
|
||||
width_multiple: 0.50 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,48 @@
|
||||
# parameters
|
||||
nc: 80 # number of classes
|
||||
depth_multiple: 1.33 # model depth multiple
|
||||
width_multiple: 1.25 # layer channel multiple
|
||||
|
||||
# anchors
|
||||
anchors:
|
||||
- [10,13, 16,30, 33,23] # P3/8
|
||||
- [30,61, 62,45, 59,119] # P4/16
|
||||
- [116,90, 156,198, 373,326] # P5/32
|
||||
|
||||
# YOLOv5 backbone
|
||||
backbone:
|
||||
# [from, number, module, args]
|
||||
[[-1, 1, Focus, [64, 3]], # 0-P1/2
|
||||
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
|
||||
[-1, 3, C3, [128]],
|
||||
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
|
||||
[-1, 9, C3, [256]],
|
||||
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
|
||||
[-1, 9, C3, [512]],
|
||||
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
|
||||
[-1, 1, SPP, [1024, [5, 9, 13]]],
|
||||
[-1, 3, C3, [1024, False]], # 9
|
||||
]
|
||||
|
||||
# YOLOv5 head
|
||||
head:
|
||||
[[-1, 1, Conv, [512, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 6], 1, Concat, [1]], # cat backbone P4
|
||||
[-1, 3, C3, [512, False]], # 13
|
||||
|
||||
[-1, 1, Conv, [256, 1, 1]],
|
||||
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
|
||||
[[-1, 4], 1, Concat, [1]], # cat backbone P3
|
||||
[-1, 3, C3, [256, False]], # 17 (P3/8-small)
|
||||
|
||||
[-1, 1, Conv, [256, 3, 2]],
|
||||
[[-1, 14], 1, Concat, [1]], # cat head P4
|
||||
[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
|
||||
|
||||
[-1, 1, Conv, [512, 3, 2]],
|
||||
[[-1, 10], 1, Concat, [1]], # cat head P5
|
||||
[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
|
||||
|
||||
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
|
||||
]
|
||||
@ -0,0 +1,15 @@
|
||||
certifi==2024.2.2
|
||||
imutils==0.5.4
|
||||
numpy==1.26.4
|
||||
pandas==2.2.1
|
||||
requests==2.31.0
|
||||
opencv-python==4.9.0.80
|
||||
matplotlib==3.8.3
|
||||
seaborn==0.13.2
|
||||
tqdm==4.66.2
|
||||
torch==2.2.1
|
||||
torchvision==0.17.1
|
||||
torch_optimizer==0.3.0
|
||||
pyyaml==6.0.1
|
||||
easydict==1.12
|
||||
scipy==1.12.0
|
||||
@ -0,0 +1,92 @@
|
||||
from deep_sort.utils.parser import get_config
|
||||
from deep_sort.deep_sort import DeepSort
|
||||
import torch
|
||||
import cv2
|
||||
|
||||
palette = (2 ** 11 - 1, 2 ** 15 - 1, 2 ** 20 - 1)
|
||||
cfg = get_config()
|
||||
cfg.merge_from_file("deep_sort/configs/deep_sort.yaml")
|
||||
deepsort = DeepSort(cfg.DEEPSORT.REID_CKPT,
|
||||
max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
|
||||
nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP, max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
|
||||
max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET,
|
||||
use_cuda=True)
|
||||
|
||||
|
||||
def plot_bboxes(image, bboxes, line_thickness=None):
|
||||
# Plots one bounding box on image img
|
||||
tl = line_thickness or round(
|
||||
0.002 * (image.shape[0] + image.shape[1]) / 2) + 1 # line/font thickness
|
||||
for (x1, y1, x2, y2, cls_id, pos_id) in bboxes:
|
||||
if cls_id in ['person']:
|
||||
color = (0, 0, 255)
|
||||
else:
|
||||
color = (0, 255, 0)
|
||||
c1, c2 = (x1, y1), (x2, y2)
|
||||
cv2.rectangle(image, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
|
||||
tf = max(tl - 1, 1) # font thickness
|
||||
t_size = cv2.getTextSize(cls_id, 0, fontScale=tl / 3, thickness=tf)[0]
|
||||
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
|
||||
cv2.rectangle(image, c1, c2, color, -1, cv2.LINE_AA) # filled
|
||||
cv2.putText(image, '{} ID-{}'.format(cls_id, pos_id), (c1[0], c1[1] - 2), 0, tl / 3,
|
||||
[225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
|
||||
|
||||
return image
|
||||
|
||||
|
||||
def update_tracker(target_detector, image):
|
||||
|
||||
new_faces = []
|
||||
_, bboxes = target_detector.detect(image)
|
||||
|
||||
bbox_xywh = []
|
||||
confs = []
|
||||
clss = []
|
||||
|
||||
for x1, y1, x2, y2, cls_id, conf in bboxes:
|
||||
|
||||
obj = [
|
||||
int((x1+x2)/2), int((y1+y2)/2),
|
||||
x2-x1, y2-y1
|
||||
]
|
||||
bbox_xywh.append(obj)
|
||||
confs.append(conf)
|
||||
clss.append(cls_id)
|
||||
|
||||
xywhs = torch.Tensor(bbox_xywh)
|
||||
confss = torch.Tensor(confs)
|
||||
|
||||
outputs = deepsort.update(xywhs, confss, clss, image)
|
||||
|
||||
bboxes2draw = []
|
||||
face_bboxes = []
|
||||
current_ids = []
|
||||
for value in list(outputs):
|
||||
x1, y1, x2, y2, cls_, track_id = value
|
||||
bboxes2draw.append(
|
||||
(x1, y1, x2, y2, cls_, track_id)
|
||||
)
|
||||
current_ids.append(track_id)
|
||||
if cls_ == 'face':
|
||||
if not track_id in target_detector.faceTracker:
|
||||
target_detector.faceTracker[track_id] = 0
|
||||
face = image[y1:y2, x1:x2]
|
||||
new_faces.append((face, track_id))
|
||||
face_bboxes.append(
|
||||
(x1, y1, x2, y2)
|
||||
)
|
||||
|
||||
ids2delete = []
|
||||
for history_id in target_detector.faceTracker:
|
||||
if not history_id in current_ids:
|
||||
target_detector.faceTracker[history_id] -= 1
|
||||
if target_detector.faceTracker[history_id] < -5:
|
||||
ids2delete.append(history_id)
|
||||
|
||||
for ids in ids2delete:
|
||||
target_detector.faceTracker.pop(ids)
|
||||
print('-[INFO] Delete track id:', ids)
|
||||
|
||||
image = plot_bboxes(image, bboxes2draw)
|
||||
|
||||
return image, new_faces, face_bboxes
|
||||
@ -0,0 +1,50 @@
|
||||
from tracker import update_tracker
|
||||
import cv2
|
||||
|
||||
|
||||
class baseDet(object):
|
||||
|
||||
def __init__(self):
|
||||
|
||||
self.img_size = 640
|
||||
self.threshold = 0.3
|
||||
self.stride = 1
|
||||
|
||||
def build_config(self):
|
||||
|
||||
self.faceTracker = {}
|
||||
self.faceClasses = {}
|
||||
self.faceLocation1 = {}
|
||||
self.faceLocation2 = {}
|
||||
self.frameCounter = 0
|
||||
self.currentCarID = 0
|
||||
self.recorded = []
|
||||
|
||||
self.font = cv2.FONT_HERSHEY_SIMPLEX
|
||||
|
||||
def feedCap(self, im):
|
||||
|
||||
retDict = {
|
||||
'frame': None,
|
||||
'faces': None,
|
||||
'list_of_ids': None,
|
||||
'face_bboxes': []
|
||||
}
|
||||
self.frameCounter += 1
|
||||
|
||||
im, faces, face_bboxes = update_tracker(self, im)
|
||||
|
||||
retDict['frame'] = im
|
||||
retDict['faces'] = faces
|
||||
retDict['face_bboxes'] = face_bboxes
|
||||
|
||||
return retDict
|
||||
|
||||
def init_model(self):
|
||||
raise EOFError("Undefined model type.")
|
||||
|
||||
def preprocess(self):
|
||||
raise EOFError("Undefined model type.")
|
||||
|
||||
def detect(self):
|
||||
raise EOFError("Undefined model type.")
|
||||
@ -0,0 +1,98 @@
|
||||
# Activation functions
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
||||
|
||||
# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
|
||||
class SiLU(nn.Module): # export-friendly version of nn.SiLU()
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
return x * torch.sigmoid(x)
|
||||
|
||||
|
||||
class Hardswish(nn.Module): # export-friendly version of nn.Hardswish()
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
# return x * F.hardsigmoid(x) # for torchscript and CoreML
|
||||
return x * F.hardtanh(x + 3, 0., 6.) / 6. # for torchscript, CoreML and ONNX
|
||||
|
||||
|
||||
# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
|
||||
class Mish(nn.Module):
|
||||
@staticmethod
|
||||
def forward(x):
|
||||
return x * F.softplus(x).tanh()
|
||||
|
||||
|
||||
class MemoryEfficientMish(nn.Module):
|
||||
class F(torch.autograd.Function):
|
||||
@staticmethod
|
||||
def forward(ctx, x):
|
||||
ctx.save_for_backward(x)
|
||||
return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x)))
|
||||
|
||||
@staticmethod
|
||||
def backward(ctx, grad_output):
|
||||
x = ctx.saved_tensors[0]
|
||||
sx = torch.sigmoid(x)
|
||||
fx = F.softplus(x).tanh()
|
||||
return grad_output * (fx + x * sx * (1 - fx * fx))
|
||||
|
||||
def forward(self, x):
|
||||
return self.F.apply(x)
|
||||
|
||||
|
||||
# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
|
||||
class FReLU(nn.Module):
|
||||
def __init__(self, c1, k=3): # ch_in, kernel
|
||||
super().__init__()
|
||||
self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
|
||||
self.bn = nn.BatchNorm2d(c1)
|
||||
|
||||
def forward(self, x):
|
||||
return torch.max(x, self.bn(self.conv(x)))
|
||||
|
||||
|
||||
# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
|
||||
class AconC(nn.Module):
|
||||
r""" ACON activation (activate or not).
|
||||
AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
|
||||
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
|
||||
"""
|
||||
|
||||
def __init__(self, c1):
|
||||
super().__init__()
|
||||
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))
|
||||
|
||||
def forward(self, x):
|
||||
dpx = (self.p1 - self.p2) * x
|
||||
return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x
|
||||
|
||||
|
||||
class MetaAconC(nn.Module):
|
||||
r""" ACON activation (activate or not).
|
||||
MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
|
||||
according to "Activate or Not: Learning Customized Activation" <https://arxiv.org/pdf/2009.04759.pdf>.
|
||||
"""
|
||||
|
||||
def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r
|
||||
super().__init__()
|
||||
c2 = max(r, c1 // r)
|
||||
self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
|
||||
self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
|
||||
self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
|
||||
# self.bn1 = nn.BatchNorm2d(c2)
|
||||
# self.bn2 = nn.BatchNorm2d(c1)
|
||||
|
||||
def forward(self, x):
|
||||
y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
|
||||
# batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
|
||||
# beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable
|
||||
beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed
|
||||
dpx = (self.p1 - self.p2) * x
|
||||
return dpx * torch.sigmoid(beta * dpx) + self.p2 * x
|
||||
@ -0,0 +1,161 @@
|
||||
# Auto-anchor utils
|
||||
|
||||
import numpy as np
|
||||
import torch
|
||||
import yaml
|
||||
from tqdm import tqdm
|
||||
|
||||
from utils.general import colorstr
|
||||
|
||||
|
||||
def check_anchor_order(m):
|
||||
# Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
|
||||
a = m.anchor_grid.prod(-1).view(-1) # anchor area
|
||||
da = a[-1] - a[0] # delta a
|
||||
ds = m.stride[-1] - m.stride[0] # delta s
|
||||
if da.sign() != ds.sign(): # same order
|
||||
print('Reversing anchor order')
|
||||
m.anchors[:] = m.anchors.flip(0)
|
||||
m.anchor_grid[:] = m.anchor_grid.flip(0)
|
||||
|
||||
|
||||
def check_anchors(dataset, model, thr=4.0, imgsz=640):
|
||||
# Check anchor fit to data, recompute if necessary
|
||||
prefix = colorstr('autoanchor: ')
|
||||
print(f'\n{prefix}Analyzing anchors... ', end='')
|
||||
m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect()
|
||||
shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
|
||||
scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale
|
||||
wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh
|
||||
|
||||
def metric(k): # compute metric
|
||||
r = wh[:, None] / k[None]
|
||||
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
|
||||
best = x.max(1)[0] # best_x
|
||||
aat = (x > 1. / thr).float().sum(1).mean() # anchors above threshold
|
||||
bpr = (best > 1. / thr).float().mean() # best possible recall
|
||||
return bpr, aat
|
||||
|
||||
anchors = m.anchor_grid.clone().cpu().view(-1, 2) # current anchors
|
||||
bpr, aat = metric(anchors)
|
||||
print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
|
||||
if bpr < 0.98: # threshold to recompute
|
||||
print('. Attempting to improve anchors, please wait...')
|
||||
na = m.anchor_grid.numel() // 2 # number of anchors
|
||||
try:
|
||||
anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
|
||||
except Exception as e:
|
||||
print(f'{prefix}ERROR: {e}')
|
||||
new_bpr = metric(anchors)[0]
|
||||
if new_bpr > bpr: # replace anchors
|
||||
anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
|
||||
m.anchor_grid[:] = anchors.clone().view_as(m.anchor_grid) # for inference
|
||||
m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss
|
||||
check_anchor_order(m)
|
||||
print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
|
||||
else:
|
||||
print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
|
||||
print('') # newline
|
||||
|
||||
|
||||
def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
|
||||
""" Creates kmeans-evolved anchors from training dataset
|
||||
|
||||
Arguments:
|
||||
path: path to dataset *.yaml, or a loaded dataset
|
||||
n: number of anchors
|
||||
img_size: image size used for training
|
||||
thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
|
||||
gen: generations to evolve anchors using genetic algorithm
|
||||
verbose: print all results
|
||||
|
||||
Return:
|
||||
k: kmeans evolved anchors
|
||||
|
||||
Usage:
|
||||
from utils.autoanchor import *; _ = kmean_anchors()
|
||||
"""
|
||||
from scipy.cluster.vq import kmeans
|
||||
|
||||
thr = 1. / thr
|
||||
prefix = colorstr('autoanchor: ')
|
||||
|
||||
def metric(k, wh): # compute metrics
|
||||
r = wh[:, None] / k[None]
|
||||
x = torch.min(r, 1. / r).min(2)[0] # ratio metric
|
||||
# x = wh_iou(wh, torch.tensor(k)) # iou metric
|
||||
return x, x.max(1)[0] # x, best_x
|
||||
|
||||
def anchor_fitness(k): # mutation fitness
|
||||
_, best = metric(torch.tensor(k, dtype=torch.float32), wh)
|
||||
return (best * (best > thr).float()).mean() # fitness
|
||||
|
||||
def print_results(k):
|
||||
k = k[np.argsort(k.prod(1))] # sort small to large
|
||||
x, best = metric(k, wh0)
|
||||
bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr
|
||||
print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
|
||||
print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
|
||||
f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
|
||||
for i, x in enumerate(k):
|
||||
print('%i,%i' % (round(x[0]), round(x[1])), end=', ' if i < len(k) - 1 else '\n') # use in *.cfg
|
||||
return k
|
||||
|
||||
if isinstance(path, str): # *.yaml file
|
||||
with open(path) as f:
|
||||
data_dict = yaml.safe_load(f) # model dict
|
||||
from utils.datasets import LoadImagesAndLabels
|
||||
dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
|
||||
else:
|
||||
dataset = path # dataset
|
||||
|
||||
# Get label wh
|
||||
shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
|
||||
wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh
|
||||
|
||||
# Filter
|
||||
i = (wh0 < 3.0).any(1).sum()
|
||||
if i:
|
||||
print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
|
||||
wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels
|
||||
# wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
|
||||
|
||||
# Kmeans calculation
|
||||
print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
|
||||
s = wh.std(0) # sigmas for whitening
|
||||
k, dist = kmeans(wh / s, n, iter=30) # points, mean distance
|
||||
assert len(k) == n, print(f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}')
|
||||
k *= s
|
||||
wh = torch.tensor(wh, dtype=torch.float32) # filtered
|
||||
wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered
|
||||
k = print_results(k)
|
||||
|
||||
# Plot
|
||||
# k, d = [None] * 20, [None] * 20
|
||||
# for i in tqdm(range(1, 21)):
|
||||
# k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance
|
||||
# fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
|
||||
# ax = ax.ravel()
|
||||
# ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
|
||||
# fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh
|
||||
# ax[0].hist(wh[wh[:, 0]<100, 0],400)
|
||||
# ax[1].hist(wh[wh[:, 1]<100, 1],400)
|
||||
# fig.savefig('wh.png', dpi=200)
|
||||
|
||||
# Evolve
|
||||
npr = np.random
|
||||
f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma
|
||||
pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:') # progress bar
|
||||
for _ in pbar:
|
||||
v = np.ones(sh)
|
||||
while (v == 1).all(): # mutate until a change occurs (prevent duplicates)
|
||||
v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
|
||||
kg = (k.copy() * v).clip(min=2.0)
|
||||
fg = anchor_fitness(kg)
|
||||
if fg > f:
|
||||
f, k = fg, kg.copy()
|
||||
pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
|
||||
if verbose:
|
||||
print_results(k)
|
||||
|
||||
return print_results(k)
|
||||
@ -0,0 +1,26 @@
|
||||
# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
|
||||
# This script will run on every instance restart, not only on first start
|
||||
# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
|
||||
|
||||
Content-Type: multipart/mixed; boundary="//"
|
||||
MIME-Version: 1.0
|
||||
|
||||
--//
|
||||
Content-Type: text/cloud-config; charset="us-ascii"
|
||||
MIME-Version: 1.0
|
||||
Content-Transfer-Encoding: 7bit
|
||||
Content-Disposition: attachment; filename="cloud-config.txt"
|
||||
|
||||
#cloud-config
|
||||
cloud_final_modules:
|
||||
- [scripts-user, always]
|
||||
|
||||
--//
|
||||
Content-Type: text/x-shellscript; charset="us-ascii"
|
||||
MIME-Version: 1.0
|
||||
Content-Transfer-Encoding: 7bit
|
||||
Content-Disposition: attachment; filename="userdata.txt"
|
||||
|
||||
#!/bin/bash
|
||||
# --- paste contents of userdata.sh here ---
|
||||
--//
|
||||
@ -0,0 +1,37 @@
|
||||
# Resume all interrupted trainings in yolov5/ dir including DDP trainings
|
||||
# Usage: $ python utils/aws/resume.py
|
||||
|
||||
import os
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import yaml
|
||||
|
||||
sys.path.append('./') # to run '$ python *.py' files in subdirectories
|
||||
|
||||
port = 0 # --master_port
|
||||
path = Path('').resolve()
|
||||
for last in path.rglob('*/**/last.pt'):
|
||||
ckpt = torch.load(last)
|
||||
if ckpt['optimizer'] is None:
|
||||
continue
|
||||
|
||||
# Load opt.yaml
|
||||
with open(last.parent.parent / 'opt.yaml') as f:
|
||||
opt = yaml.safe_load(f)
|
||||
|
||||
# Get device count
|
||||
d = opt['device'].split(',') # devices
|
||||
nd = len(d) # number of devices
|
||||
ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel
|
||||
|
||||
if ddp: # multi-GPU
|
||||
port += 1
|
||||
cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
|
||||
else: # single-GPU
|
||||
cmd = f'python train.py --resume {last}'
|
||||
|
||||
cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread
|
||||
print(cmd)
|
||||
os.system(cmd)
|
||||
@ -0,0 +1,27 @@
|
||||
#!/bin/bash
|
||||
# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
|
||||
# This script will run only once on first instance start (for a re-start script see mime.sh)
|
||||
# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
|
||||
# Use >300 GB SSD
|
||||
|
||||
cd home/ubuntu
|
||||
if [ ! -d yolov5 ]; then
|
||||
echo "Running first-time script." # install dependencies, download COCO, pull Docker
|
||||
git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5
|
||||
cd yolov5
|
||||
bash data/scripts/get_coco.sh && echo "Data done." &
|
||||
sudo docker pull ultralytics/yolov5:latest && echo "Docker done." &
|
||||
python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
|
||||
wait && echo "All tasks done." # finish background tasks
|
||||
else
|
||||
echo "Running re-start script." # resume interrupted runs
|
||||
i=0
|
||||
list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
|
||||
while IFS= read -r id; do
|
||||
((i++))
|
||||
echo "restarting container $i: $id"
|
||||
sudo docker start $id
|
||||
# sudo docker exec -it $id python train.py --resume # single-GPU
|
||||
sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
|
||||
done <<<"$list"
|
||||
fi
|
||||
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,68 @@
|
||||
# Flask REST API
|
||||
[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
|
||||
|
||||
## Requirements
|
||||
|
||||
[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
|
||||
```shell
|
||||
$ pip install Flask
|
||||
```
|
||||
|
||||
## Run
|
||||
|
||||
After Flask installation run:
|
||||
|
||||
```shell
|
||||
$ python3 restapi.py --port 5000
|
||||
```
|
||||
|
||||
Then use [curl](https://curl.se/) to perform a request:
|
||||
|
||||
```shell
|
||||
$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'`
|
||||
```
|
||||
|
||||
The model inference results are returned as a JSON response:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"class": 0,
|
||||
"confidence": 0.8900438547,
|
||||
"height": 0.9318675399,
|
||||
"name": "person",
|
||||
"width": 0.3264600933,
|
||||
"xcenter": 0.7438579798,
|
||||
"ycenter": 0.5207948685
|
||||
},
|
||||
{
|
||||
"class": 0,
|
||||
"confidence": 0.8440024257,
|
||||
"height": 0.7155083418,
|
||||
"name": "person",
|
||||
"width": 0.6546785235,
|
||||
"xcenter": 0.427829951,
|
||||
"ycenter": 0.6334488392
|
||||
},
|
||||
{
|
||||
"class": 27,
|
||||
"confidence": 0.3771208823,
|
||||
"height": 0.3902671337,
|
||||
"name": "tie",
|
||||
"width": 0.0696444362,
|
||||
"xcenter": 0.3675483763,
|
||||
"ycenter": 0.7991207838
|
||||
},
|
||||
{
|
||||
"class": 27,
|
||||
"confidence": 0.3527112305,
|
||||
"height": 0.1540903747,
|
||||
"name": "tie",
|
||||
"width": 0.0336618312,
|
||||
"xcenter": 0.7814827561,
|
||||
"ycenter": 0.5065554976
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given in `example_request.py`
|
||||
@ -0,0 +1,13 @@
|
||||
"""Perform test request"""
|
||||
import pprint
|
||||
|
||||
import requests
|
||||
|
||||
DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s"
|
||||
TEST_IMAGE = "zidane.jpg"
|
||||
|
||||
image_data = open(TEST_IMAGE, "rb").read()
|
||||
|
||||
response = requests.post(DETECTION_URL, files={"image": image_data}).json()
|
||||
|
||||
pprint.pprint(response)
|
||||
@ -0,0 +1,37 @@
|
||||
"""
|
||||
Run a rest API exposing the yolov5s object detection model
|
||||
"""
|
||||
import argparse
|
||||
import io
|
||||
|
||||
import torch
|
||||
from PIL import Image
|
||||
from flask import Flask, request
|
||||
|
||||
app = Flask(__name__)
|
||||
|
||||
DETECTION_URL = "/v1/object-detection/yolov5s"
|
||||
|
||||
|
||||
@app.route(DETECTION_URL, methods=["POST"])
|
||||
def predict():
|
||||
if not request.method == "POST":
|
||||
return
|
||||
|
||||
if request.files.get("image"):
|
||||
image_file = request.files["image"]
|
||||
image_bytes = image_file.read()
|
||||
|
||||
img = Image.open(io.BytesIO(image_bytes))
|
||||
|
||||
results = model(img, size=640) # reduce size=320 for faster inference
|
||||
return results.pandas().xyxy[0].to_json(orient="records")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model")
|
||||
parser.add_argument("--port", default=5000, type=int, help="port number")
|
||||
args = parser.parse_args()
|
||||
|
||||
model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True) # force_reload to recache
|
||||
app.run(host="0.0.0.0", port=args.port) # debug=True causes Restarting with stat
|
||||
@ -0,0 +1,692 @@
|
||||
# YOLOv5 general utils
|
||||
|
||||
import glob
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import platform
|
||||
import random
|
||||
import re
|
||||
import subprocess
|
||||
import time
|
||||
from itertools import repeat
|
||||
from multiprocessing.pool import ThreadPool
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import pkg_resources as pkg
|
||||
import torch
|
||||
import torchvision
|
||||
import yaml
|
||||
|
||||
from utils.google_utils import gsutil_getsize
|
||||
from utils.metrics import fitness
|
||||
from utils.torch_utils import init_torch_seeds
|
||||
|
||||
# Settings
|
||||
torch.set_printoptions(linewidth=320, precision=5, profile='long')
|
||||
np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5
|
||||
pd.options.display.max_columns = 10
|
||||
cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
|
||||
os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8)) # NumExpr max threads
|
||||
|
||||
|
||||
def set_logging(rank=-1, verbose=True):
|
||||
logging.basicConfig(
|
||||
format="%(message)s",
|
||||
level=logging.INFO if (verbose and rank in [-1, 0]) else logging.WARN)
|
||||
|
||||
|
||||
def init_seeds(seed=0):
|
||||
# Initialize random number generator (RNG) seeds
|
||||
random.seed(seed)
|
||||
np.random.seed(seed)
|
||||
init_torch_seeds(seed)
|
||||
|
||||
|
||||
def get_latest_run(search_dir='.'):
|
||||
# Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
|
||||
last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
|
||||
return max(last_list, key=os.path.getctime) if last_list else ''
|
||||
|
||||
|
||||
def is_docker():
|
||||
# Is environment a Docker container
|
||||
return Path('/workspace').exists() # or Path('/.dockerenv').exists()
|
||||
|
||||
|
||||
def is_colab():
|
||||
# Is environment a Google Colab instance
|
||||
try:
|
||||
import google.colab
|
||||
return True
|
||||
except Exception as e:
|
||||
return False
|
||||
|
||||
|
||||
def emojis(str=''):
|
||||
# Return platform-dependent emoji-safe version of string
|
||||
return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
|
||||
|
||||
|
||||
def file_size(file):
|
||||
# Return file size in MB
|
||||
return Path(file).stat().st_size / 1e6
|
||||
|
||||
|
||||
def check_online():
|
||||
# Check internet connectivity
|
||||
import socket
|
||||
try:
|
||||
socket.create_connection(("1.1.1.1", 443), 5) # check host accesability
|
||||
return True
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
def check_git_status():
|
||||
# Recommend 'git pull' if code is out of date
|
||||
print(colorstr('github: '), end='')
|
||||
try:
|
||||
assert Path('.git').exists(), 'skipping check (not a git repository)'
|
||||
assert not is_docker(), 'skipping check (Docker image)'
|
||||
assert check_online(), 'skipping check (offline)'
|
||||
|
||||
cmd = 'git fetch && git config --get remote.origin.url'
|
||||
url = subprocess.check_output(cmd, shell=True).decode().strip().rstrip('.git') # github repo url
|
||||
branch = subprocess.check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip() # checked out
|
||||
n = int(subprocess.check_output(f'git rev-list {branch}..origin/master --count', shell=True)) # commits behind
|
||||
if n > 0:
|
||||
s = f"⚠️ WARNING: code is out of date by {n} commit{'s' * (n > 1)}. " \
|
||||
f"Use 'git pull' to update or 'git clone {url}' to download latest."
|
||||
else:
|
||||
s = f'up to date with {url} ✅'
|
||||
print(emojis(s)) # emoji-safe
|
||||
except Exception as e:
|
||||
print(e)
|
||||
|
||||
|
||||
def check_python(minimum='3.7.0', required=True):
|
||||
# Check current python version vs. required python version
|
||||
current = platform.python_version()
|
||||
result = pkg.parse_version(current) >= pkg.parse_version(minimum)
|
||||
if required:
|
||||
assert result, f'Python {minimum} required by YOLOv5, but Python {current} is currently installed'
|
||||
return result
|
||||
|
||||
|
||||
def check_requirements(requirements='requirements.txt', exclude=()):
|
||||
# Check installed dependencies meet requirements (pass *.txt file or list of packages)
|
||||
prefix = colorstr('red', 'bold', 'requirements:')
|
||||
check_python() # check python version
|
||||
if isinstance(requirements, (str, Path)): # requirements.txt file
|
||||
file = Path(requirements)
|
||||
if not file.exists():
|
||||
print(f"{prefix} {file.resolve()} not found, check failed.")
|
||||
return
|
||||
requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
|
||||
else: # list or tuple of packages
|
||||
requirements = [x for x in requirements if x not in exclude]
|
||||
|
||||
n = 0 # number of packages updates
|
||||
for r in requirements:
|
||||
try:
|
||||
pkg.require(r)
|
||||
except Exception as e: # DistributionNotFound or VersionConflict if requirements not met
|
||||
n += 1
|
||||
print(f"{prefix} {r} not found and is required by YOLOv5, attempting auto-update...")
|
||||
try:
|
||||
print(subprocess.check_output(f"pip install '{r}'", shell=True).decode())
|
||||
except Exception as e:
|
||||
print(f'{prefix} {e}')
|
||||
|
||||
if n: # if packages updated
|
||||
source = file.resolve() if 'file' in locals() else requirements
|
||||
s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
|
||||
f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
|
||||
print(emojis(s)) # emoji-safe
|
||||
|
||||
|
||||
def check_img_size(img_size, s=32):
|
||||
# Verify img_size is a multiple of stride s
|
||||
new_size = make_divisible(img_size, int(s)) # ceil gs-multiple
|
||||
if new_size != img_size:
|
||||
print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
|
||||
return new_size
|
||||
|
||||
|
||||
def check_imshow():
|
||||
# Check if environment supports image displays
|
||||
try:
|
||||
assert not is_docker(), 'cv2.imshow() is disabled in Docker environments'
|
||||
assert not is_colab(), 'cv2.imshow() is disabled in Google Colab environments'
|
||||
cv2.imshow('test', np.zeros((1, 1, 3)))
|
||||
cv2.waitKey(1)
|
||||
cv2.destroyAllWindows()
|
||||
cv2.waitKey(1)
|
||||
return True
|
||||
except Exception as e:
|
||||
print(f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}')
|
||||
return False
|
||||
|
||||
|
||||
def check_file(file):
|
||||
# Search for file if not found
|
||||
if Path(file).is_file() or file == '':
|
||||
return file
|
||||
else:
|
||||
files = glob.glob('./**/' + file, recursive=True) # find file
|
||||
assert len(files), f'File Not Found: {file}' # assert file was found
|
||||
assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}" # assert unique
|
||||
return files[0] # return file
|
||||
|
||||
|
||||
def check_dataset(dict):
|
||||
# Download dataset if not found locally
|
||||
val, s = dict.get('val'), dict.get('download')
|
||||
if val and len(val):
|
||||
val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path
|
||||
if not all(x.exists() for x in val):
|
||||
print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
|
||||
if s and len(s): # download script
|
||||
if s.startswith('http') and s.endswith('.zip'): # URL
|
||||
f = Path(s).name # filename
|
||||
print(f'Downloading {s} ...')
|
||||
torch.hub.download_url_to_file(s, f)
|
||||
r = os.system(f'unzip -q {f} -d ../ && rm {f}') # unzip
|
||||
elif s.startswith('bash '): # bash script
|
||||
print(f'Running {s} ...')
|
||||
r = os.system(s)
|
||||
else: # python script
|
||||
r = exec(s) # return None
|
||||
print('Dataset autodownload %s\n' % ('success' if r in (0, None) else 'failure')) # print result
|
||||
else:
|
||||
raise Exception('Dataset not found.')
|
||||
|
||||
|
||||
def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1):
|
||||
# Multi-threaded file download and unzip function
|
||||
def download_one(url, dir):
|
||||
# Download 1 file
|
||||
f = dir / Path(url).name # filename
|
||||
if not f.exists():
|
||||
print(f'Downloading {url} to {f}...')
|
||||
if curl:
|
||||
os.system(f"curl -L '{url}' -o '{f}' --retry 9 -C -") # curl download, retry and resume on fail
|
||||
else:
|
||||
torch.hub.download_url_to_file(url, f, progress=True) # torch download
|
||||
if unzip and f.suffix in ('.zip', '.gz'):
|
||||
print(f'Unzipping {f}...')
|
||||
if f.suffix == '.zip':
|
||||
s = f'unzip -qo {f} -d {dir} && rm {f}' # unzip -quiet -overwrite
|
||||
elif f.suffix == '.gz':
|
||||
s = f'tar xfz {f} --directory {f.parent}' # unzip
|
||||
if delete: # delete zip file after unzip
|
||||
s += f' && rm {f}'
|
||||
os.system(s)
|
||||
|
||||
dir = Path(dir)
|
||||
dir.mkdir(parents=True, exist_ok=True) # make directory
|
||||
if threads > 1:
|
||||
pool = ThreadPool(threads)
|
||||
pool.imap(lambda x: download_one(*x), zip(url, repeat(dir))) # multi-threaded
|
||||
pool.close()
|
||||
pool.join()
|
||||
else:
|
||||
for u in tuple(url) if isinstance(url, str) else url:
|
||||
download_one(u, dir)
|
||||
|
||||
|
||||
def make_divisible(x, divisor):
|
||||
# Returns x evenly divisible by divisor
|
||||
return math.ceil(x / divisor) * divisor
|
||||
|
||||
|
||||
def clean_str(s):
|
||||
# Cleans a string by replacing special characters with underscore _
|
||||
return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
|
||||
|
||||
|
||||
def one_cycle(y1=0.0, y2=1.0, steps=100):
|
||||
# lambda function for sinusoidal ramp from y1 to y2
|
||||
return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
|
||||
|
||||
|
||||
def colorstr(*input):
|
||||
# Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world')
|
||||
*args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) # color arguments, string
|
||||
colors = {'black': '\033[30m', # basic colors
|
||||
'red': '\033[31m',
|
||||
'green': '\033[32m',
|
||||
'yellow': '\033[33m',
|
||||
'blue': '\033[34m',
|
||||
'magenta': '\033[35m',
|
||||
'cyan': '\033[36m',
|
||||
'white': '\033[37m',
|
||||
'bright_black': '\033[90m', # bright colors
|
||||
'bright_red': '\033[91m',
|
||||
'bright_green': '\033[92m',
|
||||
'bright_yellow': '\033[93m',
|
||||
'bright_blue': '\033[94m',
|
||||
'bright_magenta': '\033[95m',
|
||||
'bright_cyan': '\033[96m',
|
||||
'bright_white': '\033[97m',
|
||||
'end': '\033[0m', # misc
|
||||
'bold': '\033[1m',
|
||||
'underline': '\033[4m'}
|
||||
return ''.join(colors[x] for x in args) + f'{string}' + colors['end']
|
||||
|
||||
|
||||
def labels_to_class_weights(labels, nc=80):
|
||||
# Get class weights (inverse frequency) from training labels
|
||||
if labels[0] is None: # no labels loaded
|
||||
return torch.Tensor()
|
||||
|
||||
labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO
|
||||
classes = labels[:, 0].astype(np.int) # labels = [class xywh]
|
||||
weights = np.bincount(classes, minlength=nc) # occurrences per class
|
||||
|
||||
# Prepend gridpoint count (for uCE training)
|
||||
# gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image
|
||||
# weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start
|
||||
|
||||
weights[weights == 0] = 1 # replace empty bins with 1
|
||||
weights = 1 / weights # number of targets per class
|
||||
weights /= weights.sum() # normalize
|
||||
return torch.from_numpy(weights)
|
||||
|
||||
|
||||
def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
|
||||
# Produces image weights based on class_weights and image contents
|
||||
class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
|
||||
image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
|
||||
# index = random.choices(range(n), weights=image_weights, k=1) # weight image sample
|
||||
return image_weights
|
||||
|
||||
|
||||
def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper)
|
||||
# https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
|
||||
# a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
|
||||
# b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
|
||||
# x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco
|
||||
# x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet
|
||||
x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
|
||||
35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
|
||||
64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
|
||||
return x
|
||||
|
||||
|
||||
def xyxy2xywh(x):
|
||||
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
|
||||
y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
|
||||
y[:, 2] = x[:, 2] - x[:, 0] # width
|
||||
y[:, 3] = x[:, 3] - x[:, 1] # height
|
||||
return y
|
||||
|
||||
|
||||
def xywh2xyxy(x):
|
||||
# Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
|
||||
y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
|
||||
y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
|
||||
y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
|
||||
return y
|
||||
|
||||
|
||||
def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
|
||||
# Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x
|
||||
y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y
|
||||
y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x
|
||||
y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y
|
||||
return y
|
||||
|
||||
|
||||
def xyn2xy(x, w=640, h=640, padw=0, padh=0):
|
||||
# Convert normalized segments into pixel segments, shape (n,2)
|
||||
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
||||
y[:, 0] = w * x[:, 0] + padw # top left x
|
||||
y[:, 1] = h * x[:, 1] + padh # top left y
|
||||
return y
|
||||
|
||||
|
||||
def segment2box(segment, width=640, height=640):
|
||||
# Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
|
||||
x, y = segment.T # segment xy
|
||||
inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
|
||||
x, y, = x[inside], y[inside]
|
||||
return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4)) # xyxy
|
||||
|
||||
|
||||
def segments2boxes(segments):
|
||||
# Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
|
||||
boxes = []
|
||||
for s in segments:
|
||||
x, y = s.T # segment xy
|
||||
boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy
|
||||
return xyxy2xywh(np.array(boxes)) # cls, xywh
|
||||
|
||||
|
||||
def resample_segments(segments, n=1000):
|
||||
# Up-sample an (n,2) segment
|
||||
for i, s in enumerate(segments):
|
||||
x = np.linspace(0, len(s) - 1, n)
|
||||
xp = np.arange(len(s))
|
||||
segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy
|
||||
return segments
|
||||
|
||||
|
||||
def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
|
||||
# Rescale coords (xyxy) from img1_shape to img0_shape
|
||||
if ratio_pad is None: # calculate from img0_shape
|
||||
gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
|
||||
pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
|
||||
else:
|
||||
gain = ratio_pad[0][0]
|
||||
pad = ratio_pad[1]
|
||||
|
||||
coords[:, [0, 2]] -= pad[0] # x padding
|
||||
coords[:, [1, 3]] -= pad[1] # y padding
|
||||
coords[:, :4] /= gain
|
||||
clip_coords(coords, img0_shape)
|
||||
return coords
|
||||
|
||||
|
||||
def clip_coords(boxes, img_shape):
|
||||
# Clip bounding xyxy bounding boxes to image shape (height, width)
|
||||
boxes[:, 0].clamp_(0, img_shape[1]) # x1
|
||||
boxes[:, 1].clamp_(0, img_shape[0]) # y1
|
||||
boxes[:, 2].clamp_(0, img_shape[1]) # x2
|
||||
boxes[:, 3].clamp_(0, img_shape[0]) # y2
|
||||
|
||||
|
||||
def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
|
||||
# Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
|
||||
box2 = box2.T
|
||||
|
||||
# Get the coordinates of bounding boxes
|
||||
if x1y1x2y2: # x1, y1, x2, y2 = box1
|
||||
b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
|
||||
b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
|
||||
else: # transform from xywh to xyxy
|
||||
b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
|
||||
b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
|
||||
b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
|
||||
b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2
|
||||
|
||||
# Intersection area
|
||||
inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
|
||||
(torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)
|
||||
|
||||
# Union Area
|
||||
w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
|
||||
w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
|
||||
union = w1 * h1 + w2 * h2 - inter + eps
|
||||
|
||||
iou = inter / union
|
||||
if GIoU or DIoU or CIoU:
|
||||
cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width
|
||||
ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height
|
||||
if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
|
||||
c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared
|
||||
rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
|
||||
(b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center distance squared
|
||||
if DIoU:
|
||||
return iou - rho2 / c2 # DIoU
|
||||
elif CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
|
||||
v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
|
||||
with torch.no_grad():
|
||||
alpha = v / (v - iou + (1 + eps))
|
||||
return iou - (rho2 / c2 + v * alpha) # CIoU
|
||||
else: # GIoU https://arxiv.org/pdf/1902.09630.pdf
|
||||
c_area = cw * ch + eps # convex area
|
||||
return iou - (c_area - union) / c_area # GIoU
|
||||
else:
|
||||
return iou # IoU
|
||||
|
||||
|
||||
def box_iou(box1, box2):
|
||||
# https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
|
||||
"""
|
||||
Return intersection-over-union (Jaccard index) of boxes.
|
||||
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
|
||||
Arguments:
|
||||
box1 (Tensor[N, 4])
|
||||
box2 (Tensor[M, 4])
|
||||
Returns:
|
||||
iou (Tensor[N, M]): the NxM matrix containing the pairwise
|
||||
IoU values for every element in boxes1 and boxes2
|
||||
"""
|
||||
|
||||
def box_area(box):
|
||||
# box = 4xn
|
||||
return (box[2] - box[0]) * (box[3] - box[1])
|
||||
|
||||
area1 = box_area(box1.T)
|
||||
area2 = box_area(box2.T)
|
||||
|
||||
# inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
|
||||
inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
|
||||
return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter)
|
||||
|
||||
|
||||
def wh_iou(wh1, wh2):
|
||||
# Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2
|
||||
wh1 = wh1[:, None] # [N,1,2]
|
||||
wh2 = wh2[None] # [1,M,2]
|
||||
inter = torch.min(wh1, wh2).prod(2) # [N,M]
|
||||
return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter)
|
||||
|
||||
|
||||
def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
|
||||
labels=(), max_det=300):
|
||||
"""Runs Non-Maximum Suppression (NMS) on inference results
|
||||
|
||||
Returns:
|
||||
list of detections, on (n,6) tensor per image [xyxy, conf, cls]
|
||||
"""
|
||||
|
||||
nc = prediction.shape[2] - 5 # number of classes
|
||||
xc = prediction[..., 4] > conf_thres # candidates
|
||||
|
||||
# Checks
|
||||
assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
|
||||
assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
|
||||
|
||||
# Settings
|
||||
min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
|
||||
max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
|
||||
time_limit = 10.0 # seconds to quit after
|
||||
redundant = True # require redundant detections
|
||||
multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
|
||||
merge = False # use merge-NMS
|
||||
|
||||
t = time.time()
|
||||
output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
|
||||
for xi, x in enumerate(prediction): # image index, image inference
|
||||
# Apply constraints
|
||||
# x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
|
||||
x = x[xc[xi]] # confidence
|
||||
|
||||
# Cat apriori labels if autolabelling
|
||||
if labels and len(labels[xi]):
|
||||
l = labels[xi]
|
||||
v = torch.zeros((len(l), nc + 5), device=x.device)
|
||||
v[:, :4] = l[:, 1:5] # box
|
||||
v[:, 4] = 1.0 # conf
|
||||
v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
|
||||
x = torch.cat((x, v), 0)
|
||||
|
||||
# If none remain process next image
|
||||
if not x.shape[0]:
|
||||
continue
|
||||
|
||||
# Compute conf
|
||||
x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
|
||||
|
||||
# Box (center x, center y, width, height) to (x1, y1, x2, y2)
|
||||
box = xywh2xyxy(x[:, :4])
|
||||
|
||||
# Detections matrix nx6 (xyxy, conf, cls)
|
||||
if multi_label:
|
||||
i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
|
||||
x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
|
||||
else: # best class only
|
||||
conf, j = x[:, 5:].max(1, keepdim=True)
|
||||
x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
|
||||
|
||||
# Filter by class
|
||||
if classes is not None:
|
||||
x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
|
||||
|
||||
# Apply finite constraint
|
||||
# if not torch.isfinite(x).all():
|
||||
# x = x[torch.isfinite(x).all(1)]
|
||||
|
||||
# Check shape
|
||||
n = x.shape[0] # number of boxes
|
||||
if not n: # no boxes
|
||||
continue
|
||||
elif n > max_nms: # excess boxes
|
||||
x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
|
||||
|
||||
# Batched NMS
|
||||
c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
|
||||
boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
|
||||
i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
|
||||
if i.shape[0] > max_det: # limit detections
|
||||
i = i[:max_det]
|
||||
if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
|
||||
# update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
|
||||
iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
|
||||
weights = iou * scores[None] # box weights
|
||||
x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
|
||||
if redundant:
|
||||
i = i[iou.sum(1) > 1] # require redundancy
|
||||
|
||||
output[xi] = x[i]
|
||||
if (time.time() - t) > time_limit:
|
||||
print(f'WARNING: NMS time limit {time_limit}s exceeded')
|
||||
break # time limit exceeded
|
||||
|
||||
return output
|
||||
|
||||
|
||||
def strip_optimizer(f='best.pt', s=''): # from utils.general import *; strip_optimizer()
|
||||
# Strip optimizer from 'f' to finalize training, optionally save as 's'
|
||||
x = torch.load(f, map_location=torch.device('cpu'))
|
||||
if x.get('ema'):
|
||||
x['model'] = x['ema'] # replace model with ema
|
||||
for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates': # keys
|
||||
x[k] = None
|
||||
x['epoch'] = -1
|
||||
x['model'].half() # to FP16
|
||||
for p in x['model'].parameters():
|
||||
p.requires_grad = False
|
||||
torch.save(x, s or f)
|
||||
mb = os.path.getsize(s or f) / 1E6 # filesize
|
||||
print(f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB")
|
||||
|
||||
|
||||
def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''):
|
||||
# Print mutation results to evolve.txt (for use with train.py --evolve)
|
||||
a = '%10s' * len(hyp) % tuple(hyp.keys()) # hyperparam keys
|
||||
b = '%10.3g' * len(hyp) % tuple(hyp.values()) # hyperparam values
|
||||
c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
|
||||
print('\n%s\n%s\nEvolved fitness: %s\n' % (a, b, c))
|
||||
|
||||
if bucket:
|
||||
url = 'gs://%s/evolve.txt' % bucket
|
||||
if gsutil_getsize(url) > (os.path.getsize('evolve.txt') if os.path.exists('evolve.txt') else 0):
|
||||
os.system('gsutil cp %s .' % url) # download evolve.txt if larger than local
|
||||
|
||||
with open('evolve.txt', 'a') as f: # append result
|
||||
f.write(c + b + '\n')
|
||||
x = np.unique(np.loadtxt('evolve.txt', ndmin=2), axis=0) # load unique rows
|
||||
x = x[np.argsort(-fitness(x))] # sort
|
||||
np.savetxt('evolve.txt', x, '%10.3g') # save sort by fitness
|
||||
|
||||
# Save yaml
|
||||
for i, k in enumerate(hyp.keys()):
|
||||
hyp[k] = float(x[0, i + 7])
|
||||
with open(yaml_file, 'w') as f:
|
||||
results = tuple(x[0, :7])
|
||||
c = '%10.4g' * len(results) % results # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
|
||||
f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n')
|
||||
yaml.safe_dump(hyp, f, sort_keys=False)
|
||||
|
||||
if bucket:
|
||||
os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket)) # upload
|
||||
|
||||
|
||||
def apply_classifier(x, model, img, im0):
|
||||
# Apply a second stage classifier to yolo outputs
|
||||
im0 = [im0] if isinstance(im0, np.ndarray) else im0
|
||||
for i, d in enumerate(x): # per image
|
||||
if d is not None and len(d):
|
||||
d = d.clone()
|
||||
|
||||
# Reshape and pad cutouts
|
||||
b = xyxy2xywh(d[:, :4]) # boxes
|
||||
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square
|
||||
b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad
|
||||
d[:, :4] = xywh2xyxy(b).long()
|
||||
|
||||
# Rescale boxes from img_size to im0 size
|
||||
scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
|
||||
|
||||
# Classes
|
||||
pred_cls1 = d[:, 5].long()
|
||||
ims = []
|
||||
for j, a in enumerate(d): # per item
|
||||
cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
|
||||
im = cv2.resize(cutout, (224, 224)) # BGR
|
||||
# cv2.imwrite('test%i.jpg' % j, cutout)
|
||||
|
||||
im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
|
||||
im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32
|
||||
im /= 255.0 # 0 - 255 to 0.0 - 1.0
|
||||
ims.append(im)
|
||||
|
||||
pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction
|
||||
x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections
|
||||
|
||||
return x
|
||||
|
||||
|
||||
def save_one_box(xyxy, im, file='image.jpg', gain=1.02, pad=10, square=False, BGR=False, save=True):
|
||||
# Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop
|
||||
xyxy = torch.tensor(xyxy).view(-1, 4)
|
||||
b = xyxy2xywh(xyxy) # boxes
|
||||
if square:
|
||||
b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square
|
||||
b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad
|
||||
xyxy = xywh2xyxy(b).long()
|
||||
clip_coords(xyxy, im.shape)
|
||||
crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
|
||||
if save:
|
||||
cv2.imwrite(str(increment_path(file, mkdir=True).with_suffix('.jpg')), crop)
|
||||
return crop
|
||||
|
||||
|
||||
def increment_path(path, exist_ok=False, sep='', mkdir=False):
|
||||
# Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
|
||||
path = Path(path) # os-agnostic
|
||||
if path.exists() and not exist_ok:
|
||||
suffix = path.suffix
|
||||
path = path.with_suffix('')
|
||||
dirs = glob.glob(f"{path}{sep}*") # similar paths
|
||||
matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
|
||||
i = [int(m.groups()[0]) for m in matches if m] # indices
|
||||
n = max(i) + 1 if i else 2 # increment number
|
||||
path = Path(f"{path}{sep}{n}{suffix}") # update path
|
||||
dir = path if path.suffix == '' else path.parent # directory
|
||||
if not dir.exists() and mkdir:
|
||||
dir.mkdir(parents=True, exist_ok=True) # make directory
|
||||
return path
|
||||
@ -0,0 +1,25 @@
|
||||
FROM gcr.io/google-appengine/python
|
||||
|
||||
# Create a virtualenv for dependencies. This isolates these packages from
|
||||
# system-level packages.
|
||||
# Use -p python3 or -p python3.7 to select python version. Default is version 2.
|
||||
RUN virtualenv /env -p python3
|
||||
|
||||
# Setting these environment variables are the same as running
|
||||
# source /env/bin/activate.
|
||||
ENV VIRTUAL_ENV /env
|
||||
ENV PATH /env/bin:$PATH
|
||||
|
||||
RUN apt-get update && apt-get install -y python-opencv
|
||||
|
||||
# Copy the application's requirements.txt and run pip to install all
|
||||
# dependencies into the virtualenv.
|
||||
ADD requirements.txt /app/requirements.txt
|
||||
RUN pip install -r /app/requirements.txt
|
||||
|
||||
# Add the application source code.
|
||||
ADD . /app
|
||||
|
||||
# Run a WSGI server to serve the application. gunicorn must be declared as
|
||||
# a dependency in requirements.txt.
|
||||
CMD gunicorn -b :$PORT main:app
|
||||
@ -0,0 +1,4 @@
|
||||
# add these requirements in your app on top of the existing ones
|
||||
pip==18.1
|
||||
Flask==1.0.2
|
||||
gunicorn==19.9.0
|
||||
@ -0,0 +1,14 @@
|
||||
runtime: custom
|
||||
env: flex
|
||||
|
||||
service: yolov5app
|
||||
|
||||
liveness_check:
|
||||
initial_delay_sec: 600
|
||||
|
||||
manual_scaling:
|
||||
instances: 1
|
||||
resources:
|
||||
cpu: 1
|
||||
memory_gb: 4
|
||||
disk_size_gb: 20
|
||||
@ -0,0 +1,127 @@
|
||||
# Google utils: https://cloud.google.com/storage/docs/reference/libraries
|
||||
|
||||
import os
|
||||
import platform
|
||||
import subprocess
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
import requests
|
||||
import torch
|
||||
|
||||
|
||||
def gsutil_getsize(url=''):
|
||||
# gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
|
||||
s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8')
|
||||
return eval(s.split(' ')[0]) if len(s) else 0 # bytes
|
||||
|
||||
|
||||
def attempt_download(file, repo='ultralytics/yolov5'):
|
||||
# Attempt file download if does not exist
|
||||
file = Path(str(file).strip().replace("'", ''))
|
||||
|
||||
if not file.exists():
|
||||
file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required)
|
||||
try:
|
||||
response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api
|
||||
assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov5s.pt', 'yolov5m.pt', ...]
|
||||
tag = response['tag_name'] # i.e. 'v1.0'
|
||||
except: # fallback plan
|
||||
assets = ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt',
|
||||
'yolov5s6.pt', 'yolov5m6.pt', 'yolov5l6.pt', 'yolov5x6.pt']
|
||||
try:
|
||||
tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
|
||||
except:
|
||||
tag = 'v5.0' # current release
|
||||
|
||||
name = file.name
|
||||
if name in assets:
|
||||
msg = f'{file} missing, try downloading from https://github.com/{repo}/releases/'
|
||||
redundant = False # second download option
|
||||
try: # GitHub
|
||||
url = f'https://github.com/{repo}/releases/download/{tag}/{name}'
|
||||
print(f'Downloading {url} to {file}...')
|
||||
torch.hub.download_url_to_file(url, file)
|
||||
assert file.exists() and file.stat().st_size > 1E6 # check
|
||||
except Exception as e: # GCP
|
||||
print(f'Download error: {e}')
|
||||
assert redundant, 'No secondary mirror'
|
||||
url = f'https://storage.googleapis.com/{repo}/ckpt/{name}'
|
||||
print(f'Downloading {url} to {file}...')
|
||||
os.system(f"curl -L '{url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail
|
||||
finally:
|
||||
if not file.exists() or file.stat().st_size < 1E6: # check
|
||||
file.unlink(missing_ok=True) # remove partial downloads
|
||||
print(f'ERROR: Download failure: {msg}')
|
||||
print('')
|
||||
return
|
||||
|
||||
|
||||
def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
|
||||
# Downloads a file from Google Drive. from yolov5.utils.google_utils import *; gdrive_download()
|
||||
t = time.time()
|
||||
file = Path(file)
|
||||
cookie = Path('cookie') # gdrive cookie
|
||||
print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
|
||||
file.unlink(missing_ok=True) # remove existing file
|
||||
cookie.unlink(missing_ok=True) # remove existing cookie
|
||||
|
||||
# Attempt file download
|
||||
out = "NUL" if platform.system() == "Windows" else "/dev/null"
|
||||
os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
|
||||
if os.path.exists('cookie'): # large file
|
||||
s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
|
||||
else: # small file
|
||||
s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
|
||||
r = os.system(s) # execute, capture return
|
||||
cookie.unlink(missing_ok=True) # remove existing cookie
|
||||
|
||||
# Error check
|
||||
if r != 0:
|
||||
file.unlink(missing_ok=True) # remove partial
|
||||
print('Download error ') # raise Exception('Download error')
|
||||
return r
|
||||
|
||||
# Unzip if archive
|
||||
if file.suffix == '.zip':
|
||||
print('unzipping... ', end='')
|
||||
os.system(f'unzip -q {file}') # unzip
|
||||
file.unlink() # remove zip to free space
|
||||
|
||||
print(f'Done ({time.time() - t:.1f}s)')
|
||||
return r
|
||||
|
||||
|
||||
def get_token(cookie="./cookie"):
|
||||
with open(cookie) as f:
|
||||
for line in f:
|
||||
if "download" in line:
|
||||
return line.split()[-1]
|
||||
return ""
|
||||
|
||||
# def upload_blob(bucket_name, source_file_name, destination_blob_name):
|
||||
# # Uploads a file to a bucket
|
||||
# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
|
||||
#
|
||||
# storage_client = storage.Client()
|
||||
# bucket = storage_client.get_bucket(bucket_name)
|
||||
# blob = bucket.blob(destination_blob_name)
|
||||
#
|
||||
# blob.upload_from_filename(source_file_name)
|
||||
#
|
||||
# print('File {} uploaded to {}.'.format(
|
||||
# source_file_name,
|
||||
# destination_blob_name))
|
||||
#
|
||||
#
|
||||
# def download_blob(bucket_name, source_blob_name, destination_file_name):
|
||||
# # Uploads a blob from a bucket
|
||||
# storage_client = storage.Client()
|
||||
# bucket = storage_client.get_bucket(bucket_name)
|
||||
# blob = bucket.blob(source_blob_name)
|
||||
#
|
||||
# blob.download_to_filename(destination_file_name)
|
||||
#
|
||||
# print('Blob {} downloaded to {}.'.format(
|
||||
# source_blob_name,
|
||||
# destination_file_name))
|
||||
@ -0,0 +1,216 @@
|
||||
# Loss functions
|
||||
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from utils.general import bbox_iou
|
||||
from utils.torch_utils import is_parallel
|
||||
|
||||
|
||||
def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
|
||||
# return positive, negative label smoothing BCE targets
|
||||
return 1.0 - 0.5 * eps, 0.5 * eps
|
||||
|
||||
|
||||
class BCEBlurWithLogitsLoss(nn.Module):
|
||||
# BCEwithLogitLoss() with reduced missing label effects.
|
||||
def __init__(self, alpha=0.05):
|
||||
super(BCEBlurWithLogitsLoss, self).__init__()
|
||||
self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss()
|
||||
self.alpha = alpha
|
||||
|
||||
def forward(self, pred, true):
|
||||
loss = self.loss_fcn(pred, true)
|
||||
pred = torch.sigmoid(pred) # prob from logits
|
||||
dx = pred - true # reduce only missing label effects
|
||||
# dx = (pred - true).abs() # reduce missing label and false label effects
|
||||
alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4))
|
||||
loss *= alpha_factor
|
||||
return loss.mean()
|
||||
|
||||
|
||||
class FocalLoss(nn.Module):
|
||||
# Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
|
||||
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
|
||||
super(FocalLoss, self).__init__()
|
||||
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
|
||||
self.gamma = gamma
|
||||
self.alpha = alpha
|
||||
self.reduction = loss_fcn.reduction
|
||||
self.loss_fcn.reduction = 'none' # required to apply FL to each element
|
||||
|
||||
def forward(self, pred, true):
|
||||
loss = self.loss_fcn(pred, true)
|
||||
# p_t = torch.exp(-loss)
|
||||
# loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability
|
||||
|
||||
# TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
|
||||
pred_prob = torch.sigmoid(pred) # prob from logits
|
||||
p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
|
||||
alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
|
||||
modulating_factor = (1.0 - p_t) ** self.gamma
|
||||
loss *= alpha_factor * modulating_factor
|
||||
|
||||
if self.reduction == 'mean':
|
||||
return loss.mean()
|
||||
elif self.reduction == 'sum':
|
||||
return loss.sum()
|
||||
else: # 'none'
|
||||
return loss
|
||||
|
||||
|
||||
class QFocalLoss(nn.Module):
|
||||
# Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
|
||||
def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
|
||||
super(QFocalLoss, self).__init__()
|
||||
self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
|
||||
self.gamma = gamma
|
||||
self.alpha = alpha
|
||||
self.reduction = loss_fcn.reduction
|
||||
self.loss_fcn.reduction = 'none' # required to apply FL to each element
|
||||
|
||||
def forward(self, pred, true):
|
||||
loss = self.loss_fcn(pred, true)
|
||||
|
||||
pred_prob = torch.sigmoid(pred) # prob from logits
|
||||
alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
|
||||
modulating_factor = torch.abs(true - pred_prob) ** self.gamma
|
||||
loss *= alpha_factor * modulating_factor
|
||||
|
||||
if self.reduction == 'mean':
|
||||
return loss.mean()
|
||||
elif self.reduction == 'sum':
|
||||
return loss.sum()
|
||||
else: # 'none'
|
||||
return loss
|
||||
|
||||
|
||||
class ComputeLoss:
|
||||
# Compute losses
|
||||
def __init__(self, model, autobalance=False):
|
||||
super(ComputeLoss, self).__init__()
|
||||
device = next(model.parameters()).device # get model device
|
||||
h = model.hyp # hyperparameters
|
||||
|
||||
# Define criteria
|
||||
BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
|
||||
BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
|
||||
|
||||
# Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
|
||||
self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets
|
||||
|
||||
# Focal loss
|
||||
g = h['fl_gamma'] # focal loss gamma
|
||||
if g > 0:
|
||||
BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
|
||||
|
||||
det = model.module.model[-1] if is_parallel(model) else model.model[-1] # Detect() module
|
||||
self.balance = {3: [4.0, 1.0, 0.4]}.get(det.nl, [4.0, 1.0, 0.25, 0.06, .02]) # P3-P7
|
||||
self.ssi = list(det.stride).index(16) if autobalance else 0 # stride 16 index
|
||||
self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, model.gr, h, autobalance
|
||||
for k in 'na', 'nc', 'nl', 'anchors':
|
||||
setattr(self, k, getattr(det, k))
|
||||
|
||||
def __call__(self, p, targets): # predictions, targets, model
|
||||
device = targets.device
|
||||
lcls, lbox, lobj = torch.zeros(1, device=device), torch.zeros(1, device=device), torch.zeros(1, device=device)
|
||||
tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets
|
||||
|
||||
# Losses
|
||||
for i, pi in enumerate(p): # layer index, layer predictions
|
||||
b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
|
||||
tobj = torch.zeros_like(pi[..., 0], device=device) # target obj
|
||||
|
||||
n = b.shape[0] # number of targets
|
||||
if n:
|
||||
ps = pi[b, a, gj, gi] # prediction subset corresponding to targets
|
||||
|
||||
# Regression
|
||||
pxy = ps[:, :2].sigmoid() * 2. - 0.5
|
||||
pwh = (ps[:, 2:4].sigmoid() * 2) ** 2 * anchors[i]
|
||||
pbox = torch.cat((pxy, pwh), 1) # predicted box
|
||||
iou = bbox_iou(pbox.T, tbox[i], x1y1x2y2=False, CIoU=True) # iou(prediction, target)
|
||||
lbox += (1.0 - iou).mean() # iou loss
|
||||
|
||||
# Objectness
|
||||
tobj[b, a, gj, gi] = (1.0 - self.gr) + self.gr * iou.detach().clamp(0).type(tobj.dtype) # iou ratio
|
||||
|
||||
# Classification
|
||||
if self.nc > 1: # cls loss (only if multiple classes)
|
||||
t = torch.full_like(ps[:, 5:], self.cn, device=device) # targets
|
||||
t[range(n), tcls[i]] = self.cp
|
||||
lcls += self.BCEcls(ps[:, 5:], t) # BCE
|
||||
|
||||
# Append targets to text file
|
||||
# with open('targets.txt', 'a') as file:
|
||||
# [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
|
||||
|
||||
obji = self.BCEobj(pi[..., 4], tobj)
|
||||
lobj += obji * self.balance[i] # obj loss
|
||||
if self.autobalance:
|
||||
self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()
|
||||
|
||||
if self.autobalance:
|
||||
self.balance = [x / self.balance[self.ssi] for x in self.balance]
|
||||
lbox *= self.hyp['box']
|
||||
lobj *= self.hyp['obj']
|
||||
lcls *= self.hyp['cls']
|
||||
bs = tobj.shape[0] # batch size
|
||||
|
||||
loss = lbox + lobj + lcls
|
||||
return loss * bs, torch.cat((lbox, lobj, lcls, loss)).detach()
|
||||
|
||||
def build_targets(self, p, targets):
|
||||
# Build targets for compute_loss(), input targets(image,class,x,y,w,h)
|
||||
na, nt = self.na, targets.shape[0] # number of anchors, targets
|
||||
tcls, tbox, indices, anch = [], [], [], []
|
||||
gain = torch.ones(7, device=targets.device) # normalized to gridspace gain
|
||||
ai = torch.arange(na, device=targets.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
|
||||
targets = torch.cat((targets.repeat(na, 1, 1), ai[:, :, None]), 2) # append anchor indices
|
||||
|
||||
g = 0.5 # bias
|
||||
off = torch.tensor([[0, 0],
|
||||
[1, 0], [0, 1], [-1, 0], [0, -1], # j,k,l,m
|
||||
# [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm
|
||||
], device=targets.device).float() * g # offsets
|
||||
|
||||
for i in range(self.nl):
|
||||
anchors = self.anchors[i]
|
||||
gain[2:6] = torch.tensor(p[i].shape)[[3, 2, 3, 2]] # xyxy gain
|
||||
|
||||
# Match targets to anchors
|
||||
t = targets * gain
|
||||
if nt:
|
||||
# Matches
|
||||
r = t[:, :, 4:6] / anchors[:, None] # wh ratio
|
||||
j = torch.max(r, 1. / r).max(2)[0] < self.hyp['anchor_t'] # compare
|
||||
# j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
|
||||
t = t[j] # filter
|
||||
|
||||
# Offsets
|
||||
gxy = t[:, 2:4] # grid xy
|
||||
gxi = gain[[2, 3]] - gxy # inverse
|
||||
j, k = ((gxy % 1. < g) & (gxy > 1.)).T
|
||||
l, m = ((gxi % 1. < g) & (gxi > 1.)).T
|
||||
j = torch.stack((torch.ones_like(j), j, k, l, m))
|
||||
t = t.repeat((5, 1, 1))[j]
|
||||
offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
|
||||
else:
|
||||
t = targets[0]
|
||||
offsets = 0
|
||||
|
||||
# Define
|
||||
b, c = t[:, :2].long().T # image, class
|
||||
gxy = t[:, 2:4] # grid xy
|
||||
gwh = t[:, 4:6] # grid wh
|
||||
gij = (gxy - offsets).long()
|
||||
gi, gj = gij.T # grid xy indices
|
||||
|
||||
# Append
|
||||
a = t[:, 6].long() # anchor indices
|
||||
indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices
|
||||
tbox.append(torch.cat((gxy - gij, gwh), 1)) # box
|
||||
anch.append(anchors[a]) # anchors
|
||||
tcls.append(c) # class
|
||||
|
||||
return tcls, tbox, indices, anch
|
||||
@ -0,0 +1,223 @@
|
||||
# Model validation metrics
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
import torch
|
||||
|
||||
from . import general
|
||||
|
||||
|
||||
def fitness(x):
|
||||
# Model fitness as a weighted combination of metrics
|
||||
w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
|
||||
return (x[:, :4] * w).sum(1)
|
||||
|
||||
|
||||
def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=()):
|
||||
""" Compute the average precision, given the recall and precision curves.
|
||||
Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
|
||||
# Arguments
|
||||
tp: True positives (nparray, nx1 or nx10).
|
||||
conf: Objectness value from 0-1 (nparray).
|
||||
pred_cls: Predicted object classes (nparray).
|
||||
target_cls: True object classes (nparray).
|
||||
plot: Plot precision-recall curve at mAP@0.5
|
||||
save_dir: Plot save directory
|
||||
# Returns
|
||||
The average precision as computed in py-faster-rcnn.
|
||||
"""
|
||||
|
||||
# Sort by objectness
|
||||
i = np.argsort(-conf)
|
||||
tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
|
||||
|
||||
# Find unique classes
|
||||
unique_classes = np.unique(target_cls)
|
||||
nc = unique_classes.shape[0] # number of classes, number of detections
|
||||
|
||||
# Create Precision-Recall curve and compute AP for each class
|
||||
px, py = np.linspace(0, 1, 1000), [] # for plotting
|
||||
ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
|
||||
for ci, c in enumerate(unique_classes):
|
||||
i = pred_cls == c
|
||||
n_l = (target_cls == c).sum() # number of labels
|
||||
n_p = i.sum() # number of predictions
|
||||
|
||||
if n_p == 0 or n_l == 0:
|
||||
continue
|
||||
else:
|
||||
# Accumulate FPs and TPs
|
||||
fpc = (1 - tp[i]).cumsum(0)
|
||||
tpc = tp[i].cumsum(0)
|
||||
|
||||
# Recall
|
||||
recall = tpc / (n_l + 1e-16) # recall curve
|
||||
r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
|
||||
|
||||
# Precision
|
||||
precision = tpc / (tpc + fpc) # precision curve
|
||||
p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score
|
||||
|
||||
# AP from recall-precision curve
|
||||
for j in range(tp.shape[1]):
|
||||
ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
|
||||
if plot and j == 0:
|
||||
py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5
|
||||
|
||||
# Compute F1 (harmonic mean of precision and recall)
|
||||
f1 = 2 * p * r / (p + r + 1e-16)
|
||||
if plot:
|
||||
plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
|
||||
plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
|
||||
plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
|
||||
plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')
|
||||
|
||||
i = f1.mean(0).argmax() # max F1 index
|
||||
return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')
|
||||
|
||||
|
||||
def compute_ap(recall, precision):
|
||||
""" Compute the average precision, given the recall and precision curves
|
||||
# Arguments
|
||||
recall: The recall curve (list)
|
||||
precision: The precision curve (list)
|
||||
# Returns
|
||||
Average precision, precision curve, recall curve
|
||||
"""
|
||||
|
||||
# Append sentinel values to beginning and end
|
||||
mrec = np.concatenate(([0.], recall, [recall[-1] + 0.01]))
|
||||
mpre = np.concatenate(([1.], precision, [0.]))
|
||||
|
||||
# Compute the precision envelope
|
||||
mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
|
||||
|
||||
# Integrate area under curve
|
||||
method = 'interp' # methods: 'continuous', 'interp'
|
||||
if method == 'interp':
|
||||
x = np.linspace(0, 1, 101) # 101-point interp (COCO)
|
||||
ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate
|
||||
else: # 'continuous'
|
||||
i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes
|
||||
ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve
|
||||
|
||||
return ap, mpre, mrec
|
||||
|
||||
|
||||
class ConfusionMatrix:
|
||||
# Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
|
||||
def __init__(self, nc, conf=0.25, iou_thres=0.45):
|
||||
self.matrix = np.zeros((nc + 1, nc + 1))
|
||||
self.nc = nc # number of classes
|
||||
self.conf = conf
|
||||
self.iou_thres = iou_thres
|
||||
|
||||
def process_batch(self, detections, labels):
|
||||
"""
|
||||
Return intersection-over-union (Jaccard index) of boxes.
|
||||
Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
|
||||
Arguments:
|
||||
detections (Array[N, 6]), x1, y1, x2, y2, conf, class
|
||||
labels (Array[M, 5]), class, x1, y1, x2, y2
|
||||
Returns:
|
||||
None, updates confusion matrix accordingly
|
||||
"""
|
||||
detections = detections[detections[:, 4] > self.conf]
|
||||
gt_classes = labels[:, 0].int()
|
||||
detection_classes = detections[:, 5].int()
|
||||
iou = general.box_iou(labels[:, 1:], detections[:, :4])
|
||||
|
||||
x = torch.where(iou > self.iou_thres)
|
||||
if x[0].shape[0]:
|
||||
matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
|
||||
if x[0].shape[0] > 1:
|
||||
matches = matches[matches[:, 2].argsort()[::-1]]
|
||||
matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
|
||||
matches = matches[matches[:, 2].argsort()[::-1]]
|
||||
matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
|
||||
else:
|
||||
matches = np.zeros((0, 3))
|
||||
|
||||
n = matches.shape[0] > 0
|
||||
m0, m1, _ = matches.transpose().astype(np.int16)
|
||||
for i, gc in enumerate(gt_classes):
|
||||
j = m0 == i
|
||||
if n and sum(j) == 1:
|
||||
self.matrix[detection_classes[m1[j]], gc] += 1 # correct
|
||||
else:
|
||||
self.matrix[self.nc, gc] += 1 # background FP
|
||||
|
||||
if n:
|
||||
for i, dc in enumerate(detection_classes):
|
||||
if not any(m1 == i):
|
||||
self.matrix[dc, self.nc] += 1 # background FN
|
||||
|
||||
def matrix(self):
|
||||
return self.matrix
|
||||
|
||||
def plot(self, save_dir='', names=()):
|
||||
try:
|
||||
import seaborn as sn
|
||||
|
||||
array = self.matrix / (self.matrix.sum(0).reshape(1, self.nc + 1) + 1E-6) # normalize
|
||||
array[array < 0.005] = np.nan # don't annotate (would appear as 0.00)
|
||||
|
||||
fig = plt.figure(figsize=(12, 9), tight_layout=True)
|
||||
sn.set(font_scale=1.0 if self.nc < 50 else 0.8) # for label size
|
||||
labels = (0 < len(names) < 99) and len(names) == self.nc # apply names to ticklabels
|
||||
sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
|
||||
xticklabels=names + ['background FP'] if labels else "auto",
|
||||
yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
|
||||
fig.axes[0].set_xlabel('True')
|
||||
fig.axes[0].set_ylabel('Predicted')
|
||||
fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
def print(self):
|
||||
for i in range(self.nc + 1):
|
||||
print(' '.join(map(str, self.matrix[i])))
|
||||
|
||||
|
||||
# Plots ----------------------------------------------------------------------------------------------------------------
|
||||
|
||||
def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
|
||||
# Precision-recall curve
|
||||
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
|
||||
py = np.stack(py, axis=1)
|
||||
|
||||
if 0 < len(names) < 21: # display per-class legend if < 21 classes
|
||||
for i, y in enumerate(py.T):
|
||||
ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision)
|
||||
else:
|
||||
ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision)
|
||||
|
||||
ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean())
|
||||
ax.set_xlabel('Recall')
|
||||
ax.set_ylabel('Precision')
|
||||
ax.set_xlim(0, 1)
|
||||
ax.set_ylim(0, 1)
|
||||
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
|
||||
fig.savefig(Path(save_dir), dpi=250)
|
||||
|
||||
|
||||
def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'):
|
||||
# Metric-confidence curve
|
||||
fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
|
||||
|
||||
if 0 < len(names) < 21: # display per-class legend if < 21 classes
|
||||
for i, y in enumerate(py):
|
||||
ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric)
|
||||
else:
|
||||
ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric)
|
||||
|
||||
y = py.mean(0)
|
||||
ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}')
|
||||
ax.set_xlabel(xlabel)
|
||||
ax.set_ylabel(ylabel)
|
||||
ax.set_xlim(0, 1)
|
||||
ax.set_ylim(0, 1)
|
||||
plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
|
||||
fig.savefig(Path(save_dir), dpi=250)
|
||||
@ -0,0 +1,446 @@
|
||||
# Plotting utils
|
||||
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import random
|
||||
from copy import copy
|
||||
from pathlib import Path
|
||||
|
||||
import cv2
|
||||
import matplotlib
|
||||
import matplotlib.pyplot as plt
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
import seaborn as sns
|
||||
import torch
|
||||
import yaml
|
||||
from PIL import Image, ImageDraw, ImageFont
|
||||
|
||||
from utils.general import xywh2xyxy, xyxy2xywh
|
||||
from utils.metrics import fitness
|
||||
|
||||
# Settings
|
||||
matplotlib.rc('font', **{'size': 11})
|
||||
matplotlib.use('Agg') # for writing to files only
|
||||
|
||||
|
||||
class Colors:
|
||||
# Ultralytics color palette https://ultralytics.com/
|
||||
def __init__(self):
|
||||
# hex = matplotlib.colors.TABLEAU_COLORS.values()
|
||||
hex = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB',
|
||||
'2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7')
|
||||
self.palette = [self.hex2rgb('#' + c) for c in hex]
|
||||
self.n = len(self.palette)
|
||||
|
||||
def __call__(self, i, bgr=False):
|
||||
c = self.palette[int(i) % self.n]
|
||||
return (c[2], c[1], c[0]) if bgr else c
|
||||
|
||||
@staticmethod
|
||||
def hex2rgb(h): # rgb order (PIL)
|
||||
return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))
|
||||
|
||||
|
||||
colors = Colors() # create instance for 'from utils.plots import colors'
|
||||
|
||||
|
||||
def hist2d(x, y, n=100):
|
||||
# 2d histogram used in labels.png and evolve.png
|
||||
xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n)
|
||||
hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges))
|
||||
xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1)
|
||||
yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1)
|
||||
return np.log(hist[xidx, yidx])
|
||||
|
||||
|
||||
def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5):
|
||||
from scipy.signal import butter, filtfilt
|
||||
|
||||
# https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy
|
||||
def butter_lowpass(cutoff, fs, order):
|
||||
nyq = 0.5 * fs
|
||||
normal_cutoff = cutoff / nyq
|
||||
return butter(order, normal_cutoff, btype='low', analog=False)
|
||||
|
||||
b, a = butter_lowpass(cutoff, fs, order=order)
|
||||
return filtfilt(b, a, data) # forward-backward filter
|
||||
|
||||
|
||||
def plot_one_box(x, im, color=(128, 128, 128), label=None, line_thickness=3):
|
||||
# Plots one bounding box on image 'im' using OpenCV
|
||||
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to plot_on_box() input image.'
|
||||
tl = line_thickness or round(0.002 * (im.shape[0] + im.shape[1]) / 2) + 1 # line/font thickness
|
||||
c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
|
||||
cv2.rectangle(im, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
|
||||
if label:
|
||||
tf = max(tl - 1, 1) # font thickness
|
||||
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
|
||||
c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
|
||||
cv2.rectangle(im, c1, c2, color, -1, cv2.LINE_AA) # filled
|
||||
cv2.putText(im, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
|
||||
|
||||
|
||||
def plot_one_box_PIL(box, im, color=(128, 128, 128), label=None, line_thickness=None):
|
||||
# Plots one bounding box on image 'im' using PIL
|
||||
im = Image.fromarray(im)
|
||||
draw = ImageDraw.Draw(im)
|
||||
line_thickness = line_thickness or max(int(min(im.size) / 200), 2)
|
||||
draw.rectangle(box, width=line_thickness, outline=color) # plot
|
||||
if label:
|
||||
font = ImageFont.truetype("Arial.ttf", size=max(round(max(im.size) / 40), 12))
|
||||
txt_width, txt_height = font.getsize(label)
|
||||
draw.rectangle([box[0], box[1] - txt_height + 4, box[0] + txt_width, box[1]], fill=color)
|
||||
draw.text((box[0], box[1] - txt_height + 1), label, fill=(255, 255, 255), font=font)
|
||||
return np.asarray(im)
|
||||
|
||||
|
||||
def plot_wh_methods(): # from utils.plots import *; plot_wh_methods()
|
||||
# Compares the two methods for width-height anchor multiplication
|
||||
# https://github.com/ultralytics/yolov3/issues/168
|
||||
x = np.arange(-4.0, 4.0, .1)
|
||||
ya = np.exp(x)
|
||||
yb = torch.sigmoid(torch.from_numpy(x)).numpy() * 2
|
||||
|
||||
fig = plt.figure(figsize=(6, 3), tight_layout=True)
|
||||
plt.plot(x, ya, '.-', label='YOLOv3')
|
||||
plt.plot(x, yb ** 2, '.-', label='YOLOv5 ^2')
|
||||
plt.plot(x, yb ** 1.6, '.-', label='YOLOv5 ^1.6')
|
||||
plt.xlim(left=-4, right=4)
|
||||
plt.ylim(bottom=0, top=6)
|
||||
plt.xlabel('input')
|
||||
plt.ylabel('output')
|
||||
plt.grid()
|
||||
plt.legend()
|
||||
fig.savefig('comparison.png', dpi=200)
|
||||
|
||||
|
||||
def output_to_target(output):
|
||||
# Convert model output to target format [batch_id, class_id, x, y, w, h, conf]
|
||||
targets = []
|
||||
for i, o in enumerate(output):
|
||||
for *box, conf, cls in o.cpu().numpy():
|
||||
targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf])
|
||||
return np.array(targets)
|
||||
|
||||
|
||||
def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=640, max_subplots=16):
|
||||
# Plot image grid with labels
|
||||
|
||||
if isinstance(images, torch.Tensor):
|
||||
images = images.cpu().float().numpy()
|
||||
if isinstance(targets, torch.Tensor):
|
||||
targets = targets.cpu().numpy()
|
||||
|
||||
# un-normalise
|
||||
if np.max(images[0]) <= 1:
|
||||
images *= 255
|
||||
|
||||
tl = 3 # line thickness
|
||||
tf = max(tl - 1, 1) # font thickness
|
||||
bs, _, h, w = images.shape # batch size, _, height, width
|
||||
bs = min(bs, max_subplots) # limit plot images
|
||||
ns = np.ceil(bs ** 0.5) # number of subplots (square)
|
||||
|
||||
# Check if we should resize
|
||||
scale_factor = max_size / max(h, w)
|
||||
if scale_factor < 1:
|
||||
h = math.ceil(scale_factor * h)
|
||||
w = math.ceil(scale_factor * w)
|
||||
|
||||
mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init
|
||||
for i, img in enumerate(images):
|
||||
if i == max_subplots: # if last batch has fewer images than we expect
|
||||
break
|
||||
|
||||
block_x = int(w * (i // ns))
|
||||
block_y = int(h * (i % ns))
|
||||
|
||||
img = img.transpose(1, 2, 0)
|
||||
if scale_factor < 1:
|
||||
img = cv2.resize(img, (w, h))
|
||||
|
||||
mosaic[block_y:block_y + h, block_x:block_x + w, :] = img
|
||||
if len(targets) > 0:
|
||||
image_targets = targets[targets[:, 0] == i]
|
||||
boxes = xywh2xyxy(image_targets[:, 2:6]).T
|
||||
classes = image_targets[:, 1].astype('int')
|
||||
labels = image_targets.shape[1] == 6 # labels if no conf column
|
||||
conf = None if labels else image_targets[:, 6] # check for confidence presence (label vs pred)
|
||||
|
||||
if boxes.shape[1]:
|
||||
if boxes.max() <= 1.01: # if normalized with tolerance 0.01
|
||||
boxes[[0, 2]] *= w # scale to pixels
|
||||
boxes[[1, 3]] *= h
|
||||
elif scale_factor < 1: # absolute coords need scale if image scales
|
||||
boxes *= scale_factor
|
||||
boxes[[0, 2]] += block_x
|
||||
boxes[[1, 3]] += block_y
|
||||
for j, box in enumerate(boxes.T):
|
||||
cls = int(classes[j])
|
||||
color = colors(cls)
|
||||
cls = names[cls] if names else cls
|
||||
if labels or conf[j] > 0.25: # 0.25 conf thresh
|
||||
label = '%s' % cls if labels else '%s %.1f' % (cls, conf[j])
|
||||
plot_one_box(box, mosaic, label=label, color=color, line_thickness=tl)
|
||||
|
||||
# Draw image filename labels
|
||||
if paths:
|
||||
label = Path(paths[i]).name[:40] # trim to 40 char
|
||||
t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
|
||||
cv2.putText(mosaic, label, (block_x + 5, block_y + t_size[1] + 5), 0, tl / 3, [220, 220, 220], thickness=tf,
|
||||
lineType=cv2.LINE_AA)
|
||||
|
||||
# Image border
|
||||
cv2.rectangle(mosaic, (block_x, block_y), (block_x + w, block_y + h), (255, 255, 255), thickness=3)
|
||||
|
||||
if fname:
|
||||
r = min(1280. / max(h, w) / ns, 1.0) # ratio to limit image size
|
||||
mosaic = cv2.resize(mosaic, (int(ns * w * r), int(ns * h * r)), interpolation=cv2.INTER_AREA)
|
||||
# cv2.imwrite(fname, cv2.cvtColor(mosaic, cv2.COLOR_BGR2RGB)) # cv2 save
|
||||
Image.fromarray(mosaic).save(fname) # PIL save
|
||||
return mosaic
|
||||
|
||||
|
||||
def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''):
|
||||
# Plot LR simulating training for full epochs
|
||||
optimizer, scheduler = copy(optimizer), copy(scheduler) # do not modify originals
|
||||
y = []
|
||||
for _ in range(epochs):
|
||||
scheduler.step()
|
||||
y.append(optimizer.param_groups[0]['lr'])
|
||||
plt.plot(y, '.-', label='LR')
|
||||
plt.xlabel('epoch')
|
||||
plt.ylabel('LR')
|
||||
plt.grid()
|
||||
plt.xlim(0, epochs)
|
||||
plt.ylim(0)
|
||||
plt.savefig(Path(save_dir) / 'LR.png', dpi=200)
|
||||
plt.close()
|
||||
|
||||
|
||||
def plot_test_txt(): # from utils.plots import *; plot_test()
|
||||
# Plot test.txt histograms
|
||||
x = np.loadtxt('test.txt', dtype=np.float32)
|
||||
box = xyxy2xywh(x[:, :4])
|
||||
cx, cy = box[:, 0], box[:, 1]
|
||||
|
||||
fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True)
|
||||
ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0)
|
||||
ax.set_aspect('equal')
|
||||
plt.savefig('hist2d.png', dpi=300)
|
||||
|
||||
fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True)
|
||||
ax[0].hist(cx, bins=600)
|
||||
ax[1].hist(cy, bins=600)
|
||||
plt.savefig('hist1d.png', dpi=200)
|
||||
|
||||
|
||||
def plot_targets_txt(): # from utils.plots import *; plot_targets_txt()
|
||||
# Plot targets.txt histograms
|
||||
x = np.loadtxt('targets.txt', dtype=np.float32).T
|
||||
s = ['x targets', 'y targets', 'width targets', 'height targets']
|
||||
fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)
|
||||
ax = ax.ravel()
|
||||
for i in range(4):
|
||||
ax[i].hist(x[i], bins=100, label='%.3g +/- %.3g' % (x[i].mean(), x[i].std()))
|
||||
ax[i].legend()
|
||||
ax[i].set_title(s[i])
|
||||
plt.savefig('targets.jpg', dpi=200)
|
||||
|
||||
|
||||
def plot_study_txt(path='', x=None): # from utils.plots import *; plot_study_txt()
|
||||
# Plot study.txt generated by test.py
|
||||
fig, ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)
|
||||
# ax = ax.ravel()
|
||||
|
||||
fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
|
||||
# for f in [Path(path) / f'study_coco_{x}.txt' for x in ['yolov5s6', 'yolov5m6', 'yolov5l6', 'yolov5x6']]:
|
||||
for f in sorted(Path(path).glob('study*.txt')):
|
||||
y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T
|
||||
x = np.arange(y.shape[1]) if x is None else np.array(x)
|
||||
s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_inference (ms/img)', 't_NMS (ms/img)', 't_total (ms/img)']
|
||||
# for i in range(7):
|
||||
# ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8)
|
||||
# ax[i].set_title(s[i])
|
||||
|
||||
j = y[3].argmax() + 1
|
||||
ax2.plot(y[6, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8,
|
||||
label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
|
||||
|
||||
ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],
|
||||
'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet')
|
||||
|
||||
ax2.grid(alpha=0.2)
|
||||
ax2.set_yticks(np.arange(20, 60, 5))
|
||||
ax2.set_xlim(0, 57)
|
||||
ax2.set_ylim(30, 55)
|
||||
ax2.set_xlabel('GPU Speed (ms/img)')
|
||||
ax2.set_ylabel('COCO AP val')
|
||||
ax2.legend(loc='lower right')
|
||||
plt.savefig(str(Path(path).name) + '.png', dpi=300)
|
||||
|
||||
|
||||
def plot_labels(labels, names=(), save_dir=Path(''), loggers=None):
|
||||
# plot dataset labels
|
||||
print('Plotting labels... ')
|
||||
c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes
|
||||
nc = int(c.max() + 1) # number of classes
|
||||
x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height'])
|
||||
|
||||
# seaborn correlogram
|
||||
sns.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9))
|
||||
plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200)
|
||||
plt.close()
|
||||
|
||||
# matplotlib labels
|
||||
matplotlib.use('svg') # faster
|
||||
ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel()
|
||||
y = ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8)
|
||||
# [y[2].patches[i].set_color([x / 255 for x in colors(i)]) for i in range(nc)] # update colors bug #3195
|
||||
ax[0].set_ylabel('instances')
|
||||
if 0 < len(names) < 30:
|
||||
ax[0].set_xticks(range(len(names)))
|
||||
ax[0].set_xticklabels(names, rotation=90, fontsize=10)
|
||||
else:
|
||||
ax[0].set_xlabel('classes')
|
||||
sns.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9)
|
||||
sns.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9)
|
||||
|
||||
# rectangles
|
||||
labels[:, 1:3] = 0.5 # center
|
||||
labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000
|
||||
img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255)
|
||||
for cls, *box in labels[:1000]:
|
||||
ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls)) # plot
|
||||
ax[1].imshow(img)
|
||||
ax[1].axis('off')
|
||||
|
||||
for a in [0, 1, 2, 3]:
|
||||
for s in ['top', 'right', 'left', 'bottom']:
|
||||
ax[a].spines[s].set_visible(False)
|
||||
|
||||
plt.savefig(save_dir / 'labels.jpg', dpi=200)
|
||||
matplotlib.use('Agg')
|
||||
plt.close()
|
||||
|
||||
# loggers
|
||||
for k, v in loggers.items() or {}:
|
||||
if k == 'wandb' and v:
|
||||
v.log({"Labels": [v.Image(str(x), caption=x.name) for x in save_dir.glob('*labels*.jpg')]}, commit=False)
|
||||
|
||||
|
||||
def plot_evolution(yaml_file='data/hyp.finetune.yaml'): # from utils.plots import *; plot_evolution()
|
||||
# Plot hyperparameter evolution results in evolve.txt
|
||||
with open(yaml_file) as f:
|
||||
hyp = yaml.safe_load(f)
|
||||
x = np.loadtxt('evolve.txt', ndmin=2)
|
||||
f = fitness(x)
|
||||
# weights = (f - f.min()) ** 2 # for weighted results
|
||||
plt.figure(figsize=(10, 12), tight_layout=True)
|
||||
matplotlib.rc('font', **{'size': 8})
|
||||
for i, (k, v) in enumerate(hyp.items()):
|
||||
y = x[:, i + 7]
|
||||
# mu = (y * weights).sum() / weights.sum() # best weighted result
|
||||
mu = y[f.argmax()] # best single result
|
||||
plt.subplot(6, 5, i + 1)
|
||||
plt.scatter(y, f, c=hist2d(y, f, 20), cmap='viridis', alpha=.8, edgecolors='none')
|
||||
plt.plot(mu, f.max(), 'k+', markersize=15)
|
||||
plt.title('%s = %.3g' % (k, mu), fontdict={'size': 9}) # limit to 40 characters
|
||||
if i % 5 != 0:
|
||||
plt.yticks([])
|
||||
print('%15s: %.3g' % (k, mu))
|
||||
plt.savefig('evolve.png', dpi=200)
|
||||
print('\nPlot saved as evolve.png')
|
||||
|
||||
|
||||
def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
|
||||
# Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection()
|
||||
ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel()
|
||||
s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS']
|
||||
files = list(Path(save_dir).glob('frames*.txt'))
|
||||
for fi, f in enumerate(files):
|
||||
try:
|
||||
results = np.loadtxt(f, ndmin=2).T[:, 90:-30] # clip first and last rows
|
||||
n = results.shape[1] # number of rows
|
||||
x = np.arange(start, min(stop, n) if stop else n)
|
||||
results = results[:, x]
|
||||
t = (results[0] - results[0].min()) # set t0=0s
|
||||
results[0] = x
|
||||
for i, a in enumerate(ax):
|
||||
if i < len(results):
|
||||
label = labels[fi] if len(labels) else f.stem.replace('frames_', '')
|
||||
a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5)
|
||||
a.set_title(s[i])
|
||||
a.set_xlabel('time (s)')
|
||||
# if fi == len(files) - 1:
|
||||
# a.set_ylim(bottom=0)
|
||||
for side in ['top', 'right']:
|
||||
a.spines[side].set_visible(False)
|
||||
else:
|
||||
a.remove()
|
||||
except Exception as e:
|
||||
print('Warning: Plotting error for %s; %s' % (f, e))
|
||||
|
||||
ax[1].legend()
|
||||
plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
|
||||
|
||||
|
||||
def plot_results_overlay(start=0, stop=0): # from utils.plots import *; plot_results_overlay()
|
||||
# Plot training 'results*.txt', overlaying train and val losses
|
||||
s = ['train', 'train', 'train', 'Precision', 'mAP@0.5', 'val', 'val', 'val', 'Recall', 'mAP@0.5:0.95'] # legends
|
||||
t = ['Box', 'Objectness', 'Classification', 'P-R', 'mAP-F1'] # titles
|
||||
for f in sorted(glob.glob('results*.txt') + glob.glob('../../Downloads/results*.txt')):
|
||||
results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T
|
||||
n = results.shape[1] # number of rows
|
||||
x = range(start, min(stop, n) if stop else n)
|
||||
fig, ax = plt.subplots(1, 5, figsize=(14, 3.5), tight_layout=True)
|
||||
ax = ax.ravel()
|
||||
for i in range(5):
|
||||
for j in [i, i + 5]:
|
||||
y = results[j, x]
|
||||
ax[i].plot(x, y, marker='.', label=s[j])
|
||||
# y_smooth = butter_lowpass_filtfilt(y)
|
||||
# ax[i].plot(x, np.gradient(y_smooth), marker='.', label=s[j])
|
||||
|
||||
ax[i].set_title(t[i])
|
||||
ax[i].legend()
|
||||
ax[i].set_ylabel(f) if i == 0 else None # add filename
|
||||
fig.savefig(f.replace('.txt', '.png'), dpi=200)
|
||||
|
||||
|
||||
def plot_results(start=0, stop=0, bucket='', id=(), labels=(), save_dir=''):
|
||||
# Plot training 'results*.txt'. from utils.plots import *; plot_results(save_dir='runs/train/exp')
|
||||
fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True)
|
||||
ax = ax.ravel()
|
||||
s = ['Box', 'Objectness', 'Classification', 'Precision', 'Recall',
|
||||
'val Box', 'val Objectness', 'val Classification', 'mAP@0.5', 'mAP@0.5:0.95']
|
||||
if bucket:
|
||||
# files = ['https://storage.googleapis.com/%s/results%g.txt' % (bucket, x) for x in id]
|
||||
files = ['results%g.txt' % x for x in id]
|
||||
c = ('gsutil cp ' + '%s ' * len(files) + '.') % tuple('gs://%s/results%g.txt' % (bucket, x) for x in id)
|
||||
os.system(c)
|
||||
else:
|
||||
files = list(Path(save_dir).glob('results*.txt'))
|
||||
assert len(files), 'No results.txt files found in %s, nothing to plot.' % os.path.abspath(save_dir)
|
||||
for fi, f in enumerate(files):
|
||||
try:
|
||||
results = np.loadtxt(f, usecols=[2, 3, 4, 8, 9, 12, 13, 14, 10, 11], ndmin=2).T
|
||||
n = results.shape[1] # number of rows
|
||||
x = range(start, min(stop, n) if stop else n)
|
||||
for i in range(10):
|
||||
y = results[i, x]
|
||||
if i in [0, 1, 2, 5, 6, 7]:
|
||||
y[y == 0] = np.nan # don't show zero loss values
|
||||
# y /= y[0] # normalize
|
||||
label = labels[fi] if len(labels) else f.stem
|
||||
ax[i].plot(x, y, marker='.', label=label, linewidth=2, markersize=8)
|
||||
ax[i].set_title(s[i])
|
||||
# if i in [5, 6, 7]: # share train and val loss y axes
|
||||
# ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
|
||||
except Exception as e:
|
||||
print('Warning: Plotting error for %s; %s' % (f, e))
|
||||
|
||||
ax[1].legend()
|
||||
fig.savefig(Path(save_dir) / 'results.png', dpi=200)
|
||||
@ -0,0 +1,304 @@
|
||||
# YOLOv5 PyTorch utils
|
||||
|
||||
import datetime
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
import platform
|
||||
import subprocess
|
||||
import time
|
||||
from contextlib import contextmanager
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import torch.backends.cudnn as cudnn
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
import torchvision
|
||||
|
||||
try:
|
||||
import thop # for FLOPS computation
|
||||
except ImportError:
|
||||
thop = None
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def torch_distributed_zero_first(local_rank: int):
|
||||
"""
|
||||
Decorator to make all processes in distributed training wait for each local_master to do something.
|
||||
"""
|
||||
if local_rank not in [-1, 0]:
|
||||
torch.distributed.barrier()
|
||||
yield
|
||||
if local_rank == 0:
|
||||
torch.distributed.barrier()
|
||||
|
||||
|
||||
def init_torch_seeds(seed=0):
|
||||
# Speed-reproducibility tradeoff https://pytorch.org/docs/stable/notes/randomness.html
|
||||
torch.manual_seed(seed)
|
||||
if seed == 0: # slower, more reproducible
|
||||
cudnn.benchmark, cudnn.deterministic = False, True
|
||||
else: # faster, less reproducible
|
||||
cudnn.benchmark, cudnn.deterministic = True, False
|
||||
|
||||
|
||||
def date_modified(path=__file__):
|
||||
# return human-readable file modification date, i.e. '2021-3-26'
|
||||
t = datetime.datetime.fromtimestamp(Path(path).stat().st_mtime)
|
||||
return f'{t.year}-{t.month}-{t.day}'
|
||||
|
||||
|
||||
def git_describe(path=Path(__file__).parent): # path must be a directory
|
||||
# return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe
|
||||
s = f'git -C {path} describe --tags --long --always'
|
||||
try:
|
||||
return subprocess.check_output(s, shell=True, stderr=subprocess.STDOUT).decode()[:-1]
|
||||
except subprocess.CalledProcessError as e:
|
||||
return '' # not a git repository
|
||||
|
||||
|
||||
def select_device(device='', batch_size=None):
|
||||
# device = 'cpu' or '0' or '0,1,2,3'
|
||||
s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string
|
||||
cpu = device.lower() == 'cpu'
|
||||
if cpu:
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False
|
||||
elif device: # non-cpu device requested
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable
|
||||
assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested' # check availability
|
||||
|
||||
cuda = not cpu and torch.cuda.is_available()
|
||||
if cuda:
|
||||
devices = device.split(',') if device else range(torch.cuda.device_count()) # i.e. 0,1,6,7
|
||||
n = len(devices) # device count
|
||||
if n > 1 and batch_size: # check batch_size is divisible by device_count
|
||||
assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
|
||||
space = ' ' * len(s)
|
||||
for i, d in enumerate(devices):
|
||||
p = torch.cuda.get_device_properties(i)
|
||||
s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2}MB)\n" # bytes to MB
|
||||
else:
|
||||
s += 'CPU\n'
|
||||
|
||||
logger.info(s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s) # emoji-safe
|
||||
return torch.device('cuda:0' if cuda else 'cpu')
|
||||
|
||||
|
||||
def time_synchronized():
|
||||
# pytorch-accurate time
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.synchronize()
|
||||
return time.time()
|
||||
|
||||
|
||||
def profile(x, ops, n=100, device=None):
|
||||
# profile a pytorch module or list of modules. Example usage:
|
||||
# x = torch.randn(16, 3, 640, 640) # input
|
||||
# m1 = lambda x: x * torch.sigmoid(x)
|
||||
# m2 = nn.SiLU()
|
||||
# profile(x, [m1, m2], n=100) # profile speed over 100 iterations
|
||||
|
||||
device = device or torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
|
||||
x = x.to(device)
|
||||
x.requires_grad = True
|
||||
print(torch.__version__, device.type, torch.cuda.get_device_properties(0) if device.type == 'cuda' else '')
|
||||
print(f"\n{'Params':>12s}{'GFLOPS':>12s}{'forward (ms)':>16s}{'backward (ms)':>16s}{'input':>24s}{'output':>24s}")
|
||||
for m in ops if isinstance(ops, list) else [ops]:
|
||||
m = m.to(device) if hasattr(m, 'to') else m # device
|
||||
m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m # type
|
||||
dtf, dtb, t = 0., 0., [0., 0., 0.] # dt forward, backward
|
||||
try:
|
||||
flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPS
|
||||
except:
|
||||
flops = 0
|
||||
|
||||
for _ in range(n):
|
||||
t[0] = time_synchronized()
|
||||
y = m(x)
|
||||
t[1] = time_synchronized()
|
||||
try:
|
||||
_ = y.sum().backward()
|
||||
t[2] = time_synchronized()
|
||||
except: # no backward method
|
||||
t[2] = float('nan')
|
||||
dtf += (t[1] - t[0]) * 1000 / n # ms per op forward
|
||||
dtb += (t[2] - t[1]) * 1000 / n # ms per op backward
|
||||
|
||||
s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list'
|
||||
s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list'
|
||||
p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0 # parameters
|
||||
print(f'{p:12}{flops:12.4g}{dtf:16.4g}{dtb:16.4g}{str(s_in):>24s}{str(s_out):>24s}')
|
||||
|
||||
|
||||
def is_parallel(model):
|
||||
return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)
|
||||
|
||||
|
||||
def intersect_dicts(da, db, exclude=()):
|
||||
# Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
|
||||
return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
|
||||
|
||||
|
||||
def initialize_weights(model):
|
||||
for m in model.modules():
|
||||
t = type(m)
|
||||
if t is nn.Conv2d:
|
||||
pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
|
||||
elif t is nn.BatchNorm2d:
|
||||
m.eps = 1e-3
|
||||
m.momentum = 0.03
|
||||
elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6]:
|
||||
m.inplace = True
|
||||
|
||||
|
||||
def find_modules(model, mclass=nn.Conv2d):
|
||||
# Finds layer indices matching module class 'mclass'
|
||||
return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)]
|
||||
|
||||
|
||||
def sparsity(model):
|
||||
# Return global model sparsity
|
||||
a, b = 0., 0.
|
||||
for p in model.parameters():
|
||||
a += p.numel()
|
||||
b += (p == 0).sum()
|
||||
return b / a
|
||||
|
||||
|
||||
def prune(model, amount=0.3):
|
||||
# Prune model to requested global sparsity
|
||||
import torch.nn.utils.prune as prune
|
||||
print('Pruning model... ', end='')
|
||||
for name, m in model.named_modules():
|
||||
if isinstance(m, nn.Conv2d):
|
||||
prune.l1_unstructured(m, name='weight', amount=amount) # prune
|
||||
prune.remove(m, 'weight') # make permanent
|
||||
print(' %.3g global sparsity' % sparsity(model))
|
||||
|
||||
|
||||
def fuse_conv_and_bn(conv, bn):
|
||||
# Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/
|
||||
fusedconv = nn.Conv2d(conv.in_channels,
|
||||
conv.out_channels,
|
||||
kernel_size=conv.kernel_size,
|
||||
stride=conv.stride,
|
||||
padding=conv.padding,
|
||||
groups=conv.groups,
|
||||
bias=True).requires_grad_(False).to(conv.weight.device)
|
||||
|
||||
# prepare filters
|
||||
w_conv = conv.weight.clone().view(conv.out_channels, -1)
|
||||
w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
|
||||
fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
|
||||
|
||||
# prepare spatial bias
|
||||
b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias
|
||||
b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
|
||||
fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)
|
||||
|
||||
return fusedconv
|
||||
|
||||
|
||||
def model_info(model, verbose=False, img_size=640):
|
||||
# Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
|
||||
n_p = sum(x.numel() for x in model.parameters()) # number parameters
|
||||
n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
|
||||
if verbose:
|
||||
print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
|
||||
for i, (name, p) in enumerate(model.named_parameters()):
|
||||
name = name.replace('module_list.', '')
|
||||
print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
|
||||
(i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
|
||||
|
||||
try: # FLOPS
|
||||
from thop import profile
|
||||
stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32
|
||||
img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device) # input
|
||||
flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2 # stride GFLOPS
|
||||
img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float
|
||||
fs = ', %.1f GFLOPS' % (flops * img_size[0] / stride * img_size[1] / stride) # 640x640 GFLOPS
|
||||
except (ImportError, Exception):
|
||||
fs = ''
|
||||
|
||||
logger.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
|
||||
|
||||
|
||||
def load_classifier(name='resnet101', n=2):
|
||||
# Loads a pretrained model reshaped to n-class output
|
||||
model = torchvision.models.__dict__[name](pretrained=True)
|
||||
|
||||
# ResNet model properties
|
||||
# input_size = [3, 224, 224]
|
||||
# input_space = 'RGB'
|
||||
# input_range = [0, 1]
|
||||
# mean = [0.485, 0.456, 0.406]
|
||||
# std = [0.229, 0.224, 0.225]
|
||||
|
||||
# Reshape output to n classes
|
||||
filters = model.fc.weight.shape[1]
|
||||
model.fc.bias = nn.Parameter(torch.zeros(n), requires_grad=True)
|
||||
model.fc.weight = nn.Parameter(torch.zeros(n, filters), requires_grad=True)
|
||||
model.fc.out_features = n
|
||||
return model
|
||||
|
||||
|
||||
def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
|
||||
# scales img(bs,3,y,x) by ratio constrained to gs-multiple
|
||||
if ratio == 1.0:
|
||||
return img
|
||||
else:
|
||||
h, w = img.shape[2:]
|
||||
s = (int(h * ratio), int(w * ratio)) # new size
|
||||
img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize
|
||||
if not same_shape: # pad/crop img
|
||||
h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)]
|
||||
return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean
|
||||
|
||||
|
||||
def copy_attr(a, b, include=(), exclude=()):
|
||||
# Copy attributes from b to a, options to only include [...] and to exclude [...]
|
||||
for k, v in b.__dict__.items():
|
||||
if (len(include) and k not in include) or k.startswith('_') or k in exclude:
|
||||
continue
|
||||
else:
|
||||
setattr(a, k, v)
|
||||
|
||||
|
||||
class ModelEMA:
|
||||
""" Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
|
||||
Keep a moving average of everything in the model state_dict (parameters and buffers).
|
||||
This is intended to allow functionality like
|
||||
https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
|
||||
A smoothed version of the weights is necessary for some training schemes to perform well.
|
||||
This class is sensitive where it is initialized in the sequence of model init,
|
||||
GPU assignment and distributed training wrappers.
|
||||
"""
|
||||
|
||||
def __init__(self, model, decay=0.9999, updates=0):
|
||||
# Create EMA
|
||||
self.ema = deepcopy(model.module if is_parallel(model) else model).eval() # FP32 EMA
|
||||
# if next(model.parameters()).device.type != 'cpu':
|
||||
# self.ema.half() # FP16 EMA
|
||||
self.updates = updates # number of EMA updates
|
||||
self.decay = lambda x: decay * (1 - math.exp(-x / 2000)) # decay exponential ramp (to help early epochs)
|
||||
for p in self.ema.parameters():
|
||||
p.requires_grad_(False)
|
||||
|
||||
def update(self, model):
|
||||
# Update EMA parameters
|
||||
with torch.no_grad():
|
||||
self.updates += 1
|
||||
d = self.decay(self.updates)
|
||||
|
||||
msd = model.module.state_dict() if is_parallel(model) else model.state_dict() # model state_dict
|
||||
for k, v in self.ema.state_dict().items():
|
||||
if v.dtype.is_floating_point:
|
||||
v *= d
|
||||
v += (1. - d) * msd[k].detach()
|
||||
|
||||
def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
|
||||
# Update EMA attributes
|
||||
copy_attr(self.ema, model, include, exclude)
|
||||
@ -0,0 +1,24 @@
|
||||
import argparse
|
||||
|
||||
import yaml
|
||||
|
||||
from wandb_utils import WandbLogger
|
||||
|
||||
WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
|
||||
|
||||
|
||||
def create_dataset_artifact(opt):
|
||||
with open(opt.data) as f:
|
||||
data = yaml.safe_load(f) # data dict
|
||||
logger = WandbLogger(opt, '', None, data, job_type='Dataset Creation')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path')
|
||||
parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
|
||||
parser.add_argument('--project', type=str, default='YOLOv5', help='name of W&B Project')
|
||||
opt = parser.parse_args()
|
||||
opt.resume = False # Explicitly disallow resume check for dataset upload job
|
||||
|
||||
create_dataset_artifact(opt)
|
||||
@ -0,0 +1,318 @@
|
||||
"""Utilities and tools for tracking runs with Weights & Biases."""
|
||||
import json
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
import torch
|
||||
import yaml
|
||||
from tqdm import tqdm
|
||||
|
||||
sys.path.append(str(Path(__file__).parent.parent.parent)) # add utils/ to path
|
||||
from utils.datasets import LoadImagesAndLabels
|
||||
from utils.datasets import img2label_paths
|
||||
from utils.general import colorstr, xywh2xyxy, check_dataset, check_file
|
||||
|
||||
try:
|
||||
import wandb
|
||||
from wandb import init, finish
|
||||
except ImportError:
|
||||
wandb = None
|
||||
|
||||
WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
|
||||
|
||||
|
||||
def remove_prefix(from_string, prefix=WANDB_ARTIFACT_PREFIX):
|
||||
return from_string[len(prefix):]
|
||||
|
||||
|
||||
def check_wandb_config_file(data_config_file):
|
||||
wandb_config = '_wandb.'.join(data_config_file.rsplit('.', 1)) # updated data.yaml path
|
||||
if Path(wandb_config).is_file():
|
||||
return wandb_config
|
||||
return data_config_file
|
||||
|
||||
|
||||
def get_run_info(run_path):
|
||||
run_path = Path(remove_prefix(run_path, WANDB_ARTIFACT_PREFIX))
|
||||
run_id = run_path.stem
|
||||
project = run_path.parent.stem
|
||||
entity = run_path.parent.parent.stem
|
||||
model_artifact_name = 'run_' + run_id + '_model'
|
||||
return entity, project, run_id, model_artifact_name
|
||||
|
||||
|
||||
def check_wandb_resume(opt):
|
||||
process_wandb_config_ddp_mode(opt) if opt.global_rank not in [-1, 0] else None
|
||||
if isinstance(opt.resume, str):
|
||||
if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
if opt.global_rank not in [-1, 0]: # For resuming DDP runs
|
||||
entity, project, run_id, model_artifact_name = get_run_info(opt.resume)
|
||||
api = wandb.Api()
|
||||
artifact = api.artifact(entity + '/' + project + '/' + model_artifact_name + ':latest')
|
||||
modeldir = artifact.download()
|
||||
opt.weights = str(Path(modeldir) / "last.pt")
|
||||
return True
|
||||
return None
|
||||
|
||||
|
||||
def process_wandb_config_ddp_mode(opt):
|
||||
with open(check_file(opt.data)) as f:
|
||||
data_dict = yaml.safe_load(f) # data dict
|
||||
train_dir, val_dir = None, None
|
||||
if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX):
|
||||
api = wandb.Api()
|
||||
train_artifact = api.artifact(remove_prefix(data_dict['train']) + ':' + opt.artifact_alias)
|
||||
train_dir = train_artifact.download()
|
||||
train_path = Path(train_dir) / 'data/images/'
|
||||
data_dict['train'] = str(train_path)
|
||||
|
||||
if isinstance(data_dict['val'], str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX):
|
||||
api = wandb.Api()
|
||||
val_artifact = api.artifact(remove_prefix(data_dict['val']) + ':' + opt.artifact_alias)
|
||||
val_dir = val_artifact.download()
|
||||
val_path = Path(val_dir) / 'data/images/'
|
||||
data_dict['val'] = str(val_path)
|
||||
if train_dir or val_dir:
|
||||
ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml')
|
||||
with open(ddp_data_path, 'w') as f:
|
||||
yaml.safe_dump(data_dict, f)
|
||||
opt.data = ddp_data_path
|
||||
|
||||
|
||||
class WandbLogger():
|
||||
"""Log training runs, datasets, models, and predictions to Weights & Biases.
|
||||
|
||||
This logger sends information to W&B at wandb.ai. By default, this information
|
||||
includes hyperparameters, system configuration and metrics, model metrics,
|
||||
and basic data metrics and analyses.
|
||||
|
||||
By providing additional command line arguments to train.py, datasets,
|
||||
models and predictions can also be logged.
|
||||
|
||||
For more on how this logger is used, see the Weights & Biases documentation:
|
||||
https://docs.wandb.com/guides/integrations/yolov5
|
||||
"""
|
||||
def __init__(self, opt, name, run_id, data_dict, job_type='Training'):
|
||||
# Pre-training routine --
|
||||
self.job_type = job_type
|
||||
self.wandb, self.wandb_run, self.data_dict = wandb, None if not wandb else wandb.run, data_dict
|
||||
# It's more elegant to stick to 1 wandb.init call, but useful config data is overwritten in the WandbLogger's wandb.init call
|
||||
if isinstance(opt.resume, str): # checks resume from artifact
|
||||
if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
entity, project, run_id, model_artifact_name = get_run_info(opt.resume)
|
||||
model_artifact_name = WANDB_ARTIFACT_PREFIX + model_artifact_name
|
||||
assert wandb, 'install wandb to resume wandb runs'
|
||||
# Resume wandb-artifact:// runs here| workaround for not overwriting wandb.config
|
||||
self.wandb_run = wandb.init(id=run_id, project=project, entity=entity, resume='allow')
|
||||
opt.resume = model_artifact_name
|
||||
elif self.wandb:
|
||||
self.wandb_run = wandb.init(config=opt,
|
||||
resume="allow",
|
||||
project='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem,
|
||||
entity=opt.entity,
|
||||
name=name,
|
||||
job_type=job_type,
|
||||
id=run_id) if not wandb.run else wandb.run
|
||||
if self.wandb_run:
|
||||
if self.job_type == 'Training':
|
||||
if not opt.resume:
|
||||
wandb_data_dict = self.check_and_upload_dataset(opt) if opt.upload_dataset else data_dict
|
||||
# Info useful for resuming from artifacts
|
||||
self.wandb_run.config.opt = vars(opt)
|
||||
self.wandb_run.config.data_dict = wandb_data_dict
|
||||
self.data_dict = self.setup_training(opt, data_dict)
|
||||
if self.job_type == 'Dataset Creation':
|
||||
self.data_dict = self.check_and_upload_dataset(opt)
|
||||
else:
|
||||
prefix = colorstr('wandb: ')
|
||||
print(f"{prefix}Install Weights & Biases for YOLOv5 logging with 'pip install wandb' (recommended)")
|
||||
|
||||
def check_and_upload_dataset(self, opt):
|
||||
assert wandb, 'Install wandb to upload dataset'
|
||||
check_dataset(self.data_dict)
|
||||
config_path = self.log_dataset_artifact(check_file(opt.data),
|
||||
opt.single_cls,
|
||||
'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem)
|
||||
print("Created dataset config file ", config_path)
|
||||
with open(config_path) as f:
|
||||
wandb_data_dict = yaml.safe_load(f)
|
||||
return wandb_data_dict
|
||||
|
||||
def setup_training(self, opt, data_dict):
|
||||
self.log_dict, self.current_epoch, self.log_imgs = {}, 0, 16 # Logging Constants
|
||||
self.bbox_interval = opt.bbox_interval
|
||||
if isinstance(opt.resume, str):
|
||||
modeldir, _ = self.download_model_artifact(opt)
|
||||
if modeldir:
|
||||
self.weights = Path(modeldir) / "last.pt"
|
||||
config = self.wandb_run.config
|
||||
opt.weights, opt.save_period, opt.batch_size, opt.bbox_interval, opt.epochs, opt.hyp = str(
|
||||
self.weights), config.save_period, config.total_batch_size, config.bbox_interval, config.epochs, \
|
||||
config.opt['hyp']
|
||||
data_dict = dict(self.wandb_run.config.data_dict) # eliminates the need for config file to resume
|
||||
if 'val_artifact' not in self.__dict__: # If --upload_dataset is set, use the existing artifact, don't download
|
||||
self.train_artifact_path, self.train_artifact = self.download_dataset_artifact(data_dict.get('train'),
|
||||
opt.artifact_alias)
|
||||
self.val_artifact_path, self.val_artifact = self.download_dataset_artifact(data_dict.get('val'),
|
||||
opt.artifact_alias)
|
||||
self.result_artifact, self.result_table, self.val_table, self.weights = None, None, None, None
|
||||
if self.train_artifact_path is not None:
|
||||
train_path = Path(self.train_artifact_path) / 'data/images/'
|
||||
data_dict['train'] = str(train_path)
|
||||
if self.val_artifact_path is not None:
|
||||
val_path = Path(self.val_artifact_path) / 'data/images/'
|
||||
data_dict['val'] = str(val_path)
|
||||
self.val_table = self.val_artifact.get("val")
|
||||
self.map_val_table_path()
|
||||
if self.val_artifact is not None:
|
||||
self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
|
||||
self.result_table = wandb.Table(["epoch", "id", "prediction", "avg_confidence"])
|
||||
if opt.bbox_interval == -1:
|
||||
self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1
|
||||
return data_dict
|
||||
|
||||
def download_dataset_artifact(self, path, alias):
|
||||
if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
artifact_path = Path(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias)
|
||||
dataset_artifact = wandb.use_artifact(artifact_path.as_posix())
|
||||
assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'"
|
||||
datadir = dataset_artifact.download()
|
||||
return datadir, dataset_artifact
|
||||
return None, None
|
||||
|
||||
def download_model_artifact(self, opt):
|
||||
if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
|
||||
model_artifact = wandb.use_artifact(remove_prefix(opt.resume, WANDB_ARTIFACT_PREFIX) + ":latest")
|
||||
assert model_artifact is not None, 'Error: W&B model artifact doesn\'t exist'
|
||||
modeldir = model_artifact.download()
|
||||
epochs_trained = model_artifact.metadata.get('epochs_trained')
|
||||
total_epochs = model_artifact.metadata.get('total_epochs')
|
||||
is_finished = total_epochs is None
|
||||
assert not is_finished, 'training is finished, can only resume incomplete runs.'
|
||||
return modeldir, model_artifact
|
||||
return None, None
|
||||
|
||||
def log_model(self, path, opt, epoch, fitness_score, best_model=False):
|
||||
model_artifact = wandb.Artifact('run_' + wandb.run.id + '_model', type='model', metadata={
|
||||
'original_url': str(path),
|
||||
'epochs_trained': epoch + 1,
|
||||
'save period': opt.save_period,
|
||||
'project': opt.project,
|
||||
'total_epochs': opt.epochs,
|
||||
'fitness_score': fitness_score
|
||||
})
|
||||
model_artifact.add_file(str(path / 'last.pt'), name='last.pt')
|
||||
wandb.log_artifact(model_artifact,
|
||||
aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), 'best' if best_model else ''])
|
||||
print("Saving model artifact on epoch ", epoch + 1)
|
||||
|
||||
def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
|
||||
with open(data_file) as f:
|
||||
data = yaml.safe_load(f) # data dict
|
||||
nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names'])
|
||||
names = {k: v for k, v in enumerate(names)} # to index dictionary
|
||||
self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(
|
||||
data['train'], rect=True, batch_size=1), names, name='train') if data.get('train') else None
|
||||
self.val_artifact = self.create_dataset_table(LoadImagesAndLabels(
|
||||
data['val'], rect=True, batch_size=1), names, name='val') if data.get('val') else None
|
||||
if data.get('train'):
|
||||
data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train')
|
||||
if data.get('val'):
|
||||
data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val')
|
||||
path = data_file if overwrite_config else '_wandb.'.join(data_file.rsplit('.', 1)) # updated data.yaml path
|
||||
data.pop('download', None)
|
||||
with open(path, 'w') as f:
|
||||
yaml.safe_dump(data, f)
|
||||
|
||||
if self.job_type == 'Training': # builds correct artifact pipeline graph
|
||||
self.wandb_run.use_artifact(self.val_artifact)
|
||||
self.wandb_run.use_artifact(self.train_artifact)
|
||||
self.val_artifact.wait()
|
||||
self.val_table = self.val_artifact.get('val')
|
||||
self.map_val_table_path()
|
||||
else:
|
||||
self.wandb_run.log_artifact(self.train_artifact)
|
||||
self.wandb_run.log_artifact(self.val_artifact)
|
||||
return path
|
||||
|
||||
def map_val_table_path(self):
|
||||
self.val_table_map = {}
|
||||
print("Mapping dataset")
|
||||
for i, data in enumerate(tqdm(self.val_table.data)):
|
||||
self.val_table_map[data[3]] = data[0]
|
||||
|
||||
def create_dataset_table(self, dataset, class_to_id, name='dataset'):
|
||||
# TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging
|
||||
artifact = wandb.Artifact(name=name, type="dataset")
|
||||
img_files = tqdm([dataset.path]) if isinstance(dataset.path, str) and Path(dataset.path).is_dir() else None
|
||||
img_files = tqdm(dataset.img_files) if not img_files else img_files
|
||||
for img_file in img_files:
|
||||
if Path(img_file).is_dir():
|
||||
artifact.add_dir(img_file, name='data/images')
|
||||
labels_path = 'labels'.join(dataset.path.rsplit('images', 1))
|
||||
artifact.add_dir(labels_path, name='data/labels')
|
||||
else:
|
||||
artifact.add_file(img_file, name='data/images/' + Path(img_file).name)
|
||||
label_file = Path(img2label_paths([img_file])[0])
|
||||
artifact.add_file(str(label_file),
|
||||
name='data/labels/' + label_file.name) if label_file.exists() else None
|
||||
table = wandb.Table(columns=["id", "train_image", "Classes", "name"])
|
||||
class_set = wandb.Classes([{'id': id, 'name': name} for id, name in class_to_id.items()])
|
||||
for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)):
|
||||
box_data, img_classes = [], {}
|
||||
for cls, *xywh in labels[:, 1:].tolist():
|
||||
cls = int(cls)
|
||||
box_data.append({"position": {"middle": [xywh[0], xywh[1]], "width": xywh[2], "height": xywh[3]},
|
||||
"class_id": cls,
|
||||
"box_caption": "%s" % (class_to_id[cls])})
|
||||
img_classes[cls] = class_to_id[cls]
|
||||
boxes = {"ground_truth": {"box_data": box_data, "class_labels": class_to_id}} # inference-space
|
||||
table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), json.dumps(img_classes),
|
||||
Path(paths).name)
|
||||
artifact.add(table, name)
|
||||
return artifact
|
||||
|
||||
def log_training_progress(self, predn, path, names):
|
||||
if self.val_table and self.result_table:
|
||||
class_set = wandb.Classes([{'id': id, 'name': name} for id, name in names.items()])
|
||||
box_data = []
|
||||
total_conf = 0
|
||||
for *xyxy, conf, cls in predn.tolist():
|
||||
if conf >= 0.25:
|
||||
box_data.append(
|
||||
{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
|
||||
"class_id": int(cls),
|
||||
"box_caption": "%s %.3f" % (names[cls], conf),
|
||||
"scores": {"class_score": conf},
|
||||
"domain": "pixel"})
|
||||
total_conf = total_conf + conf
|
||||
boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space
|
||||
id = self.val_table_map[Path(path).name]
|
||||
self.result_table.add_data(self.current_epoch,
|
||||
id,
|
||||
wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set),
|
||||
total_conf / max(1, len(box_data))
|
||||
)
|
||||
|
||||
def log(self, log_dict):
|
||||
if self.wandb_run:
|
||||
for key, value in log_dict.items():
|
||||
self.log_dict[key] = value
|
||||
|
||||
def end_epoch(self, best_result=False):
|
||||
if self.wandb_run:
|
||||
wandb.log(self.log_dict)
|
||||
self.log_dict = {}
|
||||
if self.result_artifact:
|
||||
train_results = wandb.JoinedTable(self.val_table, self.result_table, "id")
|
||||
self.result_artifact.add(train_results, 'result')
|
||||
wandb.log_artifact(self.result_artifact, aliases=['latest', 'last', 'epoch ' + str(self.current_epoch),
|
||||
('best' if best_result else '')])
|
||||
self.result_table = wandb.Table(["epoch", "id", "prediction", "avg_confidence"])
|
||||
self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
|
||||
|
||||
def finish_run(self):
|
||||
if self.wandb_run:
|
||||
if self.log_dict:
|
||||
wandb.log(self.log_dict)
|
||||
wandb.run.finish()
|
||||
Binary file not shown.
Loading…
Reference in new issue