更改

src/Guide_stick_system/MonocularDistanceDetect-YOLOV5-RKNN-CPP-MultiThread

@@ -1 +0,0 @@
-Subproject commit 64a5c7595d7404f78caf82348af9ae30b105f5b4

src/Guide_stick_system/image_recognition/LICENSE

@@ -1,674 +0,0 @@
-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>.

src/Guide_stick_system/image_recognition/data/Argoverse.yaml

@@ -1,67 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
-# Example usage: python train.py --data Argoverse.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── Argoverse  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/Argoverse  # dataset root dir
-train: Argoverse-1.1/images/train/  # train images (relative to 'path') 39384 images
-val: Argoverse-1.1/images/val/  # val images (relative to 'path') 15062 images
-test: Argoverse-1.1/images/test/  # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
-
-# Classes
-nc: 8  # number of classes
-names: ['person',  'bicycle',  'car',  'motorcycle',  'bus',  'truck',  'traffic_light',  'stop_sign']  # class names
-
-
-# Download script/URL (optional) ---------------------------------------------------------------------------------------
-download: |
-  import json
-
-  from tqdm import tqdm
-  from utils.general import download, Path
-
-
-  def argoverse2yolo(set):
-      labels = {}
-      a = json.load(open(set, "rb"))
-      for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."):
-          img_id = annot['image_id']
-          img_name = a['images'][img_id]['name']
-          img_label_name = img_name[:-3] + "txt"
-
-          cls = annot['category_id']  # instance class id
-          x_center, y_center, width, height = annot['bbox']
-          x_center = (x_center + width / 2) / 1920.0  # offset and scale
-          y_center = (y_center + height / 2) / 1200.0  # offset and scale
-          width /= 1920.0  # scale
-          height /= 1200.0  # scale
-
-          img_dir = set.parents[2] / 'Argoverse-1.1' / 'labels' / a['seq_dirs'][a['images'][annot['image_id']]['sid']]
-          if not img_dir.exists():
-              img_dir.mkdir(parents=True, exist_ok=True)
-
-          k = str(img_dir / img_label_name)
-          if k not in labels:
-              labels[k] = []
-          labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n")
-
-      for k in labels:
-          with open(k, "w") as f:
-              f.writelines(labels[k])
-
-
-  # Download
-  dir = Path('../datasets/Argoverse')  # dataset root dir
-  urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip']
-  download(urls, dir=dir, delete=False)
-
-  # Convert
-  annotations_dir = 'Argoverse-HD/annotations/'
-  (dir / 'Argoverse-1.1' / 'tracking').rename(dir / 'Argoverse-1.1' / 'images')  # rename 'tracking' to 'images'
-  for d in "train.json", "val.json":
-      argoverse2yolo(dir / annotations_dir / d)  # convert VisDrone annotations to YOLO labels

src/Guide_stick_system/image_recognition/data/GlobalWheat2020.yaml

@@ -1,53 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Global Wheat 2020 dataset http://www.global-wheat.com/
-# Example usage: python train.py --data GlobalWheat2020.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── GlobalWheat2020  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/GlobalWheat2020  # dataset root dir
-train: # train images (relative to 'path') 3422 images
-  - images/arvalis_1
-  - images/arvalis_2
-  - images/arvalis_3
-  - images/ethz_1
-  - images/rres_1
-  - images/inrae_1
-  - images/usask_1
-val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1)
-  - images/ethz_1
-test: # test images (optional) 1276 images
-  - images/utokyo_1
-  - images/utokyo_2
-  - images/nau_1
-  - images/uq_1
-
-# Classes
-nc: 1  # number of classes
-names: ['wheat_head']  # class names
-
-
-# Download script/URL (optional) ---------------------------------------------------------------------------------------
-download: |
-  from utils.general import download, Path
-
-  # Download
-  dir = Path(yaml['path'])  # dataset root dir
-  urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
-  download(urls, dir=dir)
-
-  # Make Directories
-  for p in 'annotations', 'images', 'labels':
-      (dir / p).mkdir(parents=True, exist_ok=True)
-
-  # Move
-  for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
-           'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
-      (dir / p).rename(dir / 'images' / p)  # move to /images
-      f = (dir / p).with_suffix('.json')  # json file
-      if f.exists():
-          f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations

src/Guide_stick_system/image_recognition/data/Objects365.yaml

@@ -1,112 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Objects365 dataset https://www.objects365.org/
-# Example usage: python train.py --data Objects365.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── Objects365  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/Objects365  # dataset root dir
-train: images/train  # train images (relative to 'path') 1742289 images
-val: images/val # val images (relative to 'path') 80000 images
-test:  # test images (optional)
-
-# Classes
-nc: 365  # number of classes
-names: ['Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Glasses', 'Bottle', 'Desk', 'Cup',
-        'Street Lights', 'Cabinet/shelf', 'Handbag/Satchel', 'Bracelet', 'Plate', 'Picture/Frame', 'Helmet', 'Book',
-        'Gloves', 'Storage box', 'Boat', 'Leather Shoes', 'Flower', 'Bench', 'Potted Plant', 'Bowl/Basin', 'Flag',
-        'Pillow', 'Boots', 'Vase', 'Microphone', 'Necklace', 'Ring', 'SUV', 'Wine Glass', 'Belt', 'Monitor/TV',
-        'Backpack', 'Umbrella', 'Traffic Light', 'Speaker', 'Watch', 'Tie', 'Trash bin Can', 'Slippers', 'Bicycle',
-        'Stool', 'Barrel/bucket', 'Van', 'Couch', 'Sandals', 'Basket', 'Drum', 'Pen/Pencil', 'Bus', 'Wild Bird',
-        'High Heels', 'Motorcycle', 'Guitar', 'Carpet', 'Cell Phone', 'Bread', 'Camera', 'Canned', 'Truck',
-        'Traffic cone', 'Cymbal', 'Lifesaver', 'Towel', 'Stuffed Toy', 'Candle', 'Sailboat', 'Laptop', 'Awning',
-        'Bed', 'Faucet', 'Tent', 'Horse', 'Mirror', 'Power outlet', 'Sink', 'Apple', 'Air Conditioner', 'Knife',
-        'Hockey Stick', 'Paddle', 'Pickup Truck', 'Fork', 'Traffic Sign', 'Balloon', 'Tripod', 'Dog', 'Spoon', 'Clock',
-        'Pot', 'Cow', 'Cake', 'Dinning Table', 'Sheep', 'Hanger', 'Blackboard/Whiteboard', 'Napkin', 'Other Fish',
-        'Orange/Tangerine', 'Toiletry', 'Keyboard', 'Tomato', 'Lantern', 'Machinery Vehicle', 'Fan',
-        'Green Vegetables', 'Banana', 'Baseball Glove', 'Airplane', 'Mouse', 'Train', 'Pumpkin', 'Soccer', 'Skiboard',
-        'Luggage', 'Nightstand', 'Tea pot', 'Telephone', 'Trolley', 'Head Phone', 'Sports Car', 'Stop Sign',
-        'Dessert', 'Scooter', 'Stroller', 'Crane', 'Remote', 'Refrigerator', 'Oven', 'Lemon', 'Duck', 'Baseball Bat',
-        'Surveillance Camera', 'Cat', 'Jug', 'Broccoli', 'Piano', 'Pizza', 'Elephant', 'Skateboard', 'Surfboard',
-        'Gun', 'Skating and Skiing shoes', 'Gas stove', 'Donut', 'Bow Tie', 'Carrot', 'Toilet', 'Kite', 'Strawberry',
-        'Other Balls', 'Shovel', 'Pepper', 'Computer Box', 'Toilet Paper', 'Cleaning Products', 'Chopsticks',
-        'Microwave', 'Pigeon', 'Baseball', 'Cutting/chopping Board', 'Coffee Table', 'Side Table', 'Scissors',
-        'Marker', 'Pie', 'Ladder', 'Snowboard', 'Cookies', 'Radiator', 'Fire Hydrant', 'Basketball', 'Zebra', 'Grape',
-        'Giraffe', 'Potato', 'Sausage', 'Tricycle', 'Violin', 'Egg', 'Fire Extinguisher', 'Candy', 'Fire Truck',
-        'Billiards', 'Converter', 'Bathtub', 'Wheelchair', 'Golf Club', 'Briefcase', 'Cucumber', 'Cigar/Cigarette',
-        'Paint Brush', 'Pear', 'Heavy Truck', 'Hamburger', 'Extractor', 'Extension Cord', 'Tong', 'Tennis Racket',
-        'Folder', 'American Football', 'earphone', 'Mask', 'Kettle', 'Tennis', 'Ship', 'Swing', 'Coffee Machine',
-        'Slide', 'Carriage', 'Onion', 'Green beans', 'Projector', 'Frisbee', 'Washing Machine/Drying Machine',
-        'Chicken', 'Printer', 'Watermelon', 'Saxophone', 'Tissue', 'Toothbrush', 'Ice cream', 'Hot-air balloon',
-        'Cello', 'French Fries', 'Scale', 'Trophy', 'Cabbage', 'Hot dog', 'Blender', 'Peach', 'Rice', 'Wallet/Purse',
-        'Volleyball', 'Deer', 'Goose', 'Tape', 'Tablet', 'Cosmetics', 'Trumpet', 'Pineapple', 'Golf Ball',
-        'Ambulance', 'Parking meter', 'Mango', 'Key', 'Hurdle', 'Fishing Rod', 'Medal', 'Flute', 'Brush', 'Penguin',
-        'Megaphone', 'Corn', 'Lettuce', 'Garlic', 'Swan', 'Helicopter', 'Green Onion', 'Sandwich', 'Nuts',
-        'Speed Limit Sign', 'Induction Cooker', 'Broom', 'Trombone', 'Plum', 'Rickshaw', 'Goldfish', 'Kiwi fruit',
-        'Router/modem', 'Poker Card', 'Toaster', 'Shrimp', 'Sushi', 'Cheese', 'Notepaper', 'Cherry', 'Pliers', 'CD',
-        'Pasta', 'Hammer', 'Cue', 'Avocado', 'Hamimelon', 'Flask', 'Mushroom', 'Screwdriver', 'Soap', 'Recorder',
-        'Bear', 'Eggplant', 'Board Eraser', 'Coconut', 'Tape Measure/Ruler', 'Pig', 'Showerhead', 'Globe', 'Chips',
-        'Steak', 'Crosswalk Sign', 'Stapler', 'Camel', 'Formula 1', 'Pomegranate', 'Dishwasher', 'Crab',
-        'Hoverboard', 'Meat ball', 'Rice Cooker', 'Tuba', 'Calculator', 'Papaya', 'Antelope', 'Parrot', 'Seal',
-        'Butterfly', 'Dumbbell', 'Donkey', 'Lion', 'Urinal', 'Dolphin', 'Electric Drill', 'Hair Dryer', 'Egg tart',
-        'Jellyfish', 'Treadmill', 'Lighter', 'Grapefruit', 'Game board', 'Mop', 'Radish', 'Baozi', 'Target', 'French',
-        'Spring Rolls', 'Monkey', 'Rabbit', 'Pencil Case', 'Yak', 'Red Cabbage', 'Binoculars', 'Asparagus', 'Barbell',
-        'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil',
-        'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis']
-
-
-# Download script/URL (optional) ---------------------------------------------------------------------------------------
-download: |
-  from pycocotools.coco import COCO
-  from tqdm import tqdm
-
-  from utils.general import Path, download, np, xyxy2xywhn
-
-  # Make Directories
-  dir = Path(yaml['path'])  # dataset root dir
-  for p in 'images', 'labels':
-      (dir / p).mkdir(parents=True, exist_ok=True)
-      for q in 'train', 'val':
-          (dir / p / q).mkdir(parents=True, exist_ok=True)
-
-  # Train, Val Splits
-  for split, patches in [('train', 50 + 1), ('val', 43 + 1)]:
-      print(f"Processing {split} in {patches} patches ...")
-      images, labels = dir / 'images' / split, dir / 'labels' / split
-
-      # Download
-      url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/"
-      if split == 'train':
-          download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir, delete=False)  # annotations json
-          download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, delete=False, threads=8)
-      elif split == 'val':
-          download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir, delete=False)  # annotations json
-          download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, delete=False, threads=8)
-          download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, delete=False, threads=8)
-
-      # Move
-      for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'):
-          f.rename(images / f.name)  # move to /images/{split}
-
-      # Labels
-      coco = COCO(dir / f'zhiyuan_objv2_{split}.json')
-      names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
-      for cid, cat in enumerate(names):
-          catIds = coco.getCatIds(catNms=[cat])
-          imgIds = coco.getImgIds(catIds=catIds)
-          for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
-              width, height = im["width"], im["height"]
-              path = Path(im["file_name"])  # image filename
-              try:
-                  with open(labels / path.with_suffix('.txt').name, 'a') as file:
-                      annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
-                      for a in coco.loadAnns(annIds):
-                          x, y, w, h = a['bbox']  # bounding box in xywh (xy top-left corner)
-                          xyxy = np.array([x, y, x + w, y + h])[None]  # pixels(1,4)
-                          x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0]  # normalized and clipped
-                          file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n")
-              except Exception as e:
-                  print(e)

src/Guide_stick_system/image_recognition/data/SKU-110K.yaml

@@ -1,52 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19
-# Example usage: python train.py --data SKU-110K.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── SKU-110K  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/SKU-110K  # dataset root dir
-train: train.txt  # train images (relative to 'path')  8219 images
-val: val.txt  # val images (relative to 'path')  588 images
-test: test.txt  # test images (optional)  2936 images
-
-# Classes
-nc: 1  # number of classes
-names: ['object']  # class names
-
-
-# Download script/URL (optional) ---------------------------------------------------------------------------------------
-download: |
-  import shutil
-  from tqdm import tqdm
-  from utils.general import np, pd, Path, download, xyxy2xywh
-
-  # Download
-  dir = Path(yaml['path'])  # dataset root dir
-  parent = Path(dir.parent)  # download dir
-  urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz']
-  download(urls, dir=parent, delete=False)
-
-  # Rename directories
-  if dir.exists():
-      shutil.rmtree(dir)
-  (parent / 'SKU110K_fixed').rename(dir)  # rename dir
-  (dir / 'labels').mkdir(parents=True, exist_ok=True)  # create labels dir
-
-  # Convert labels
-  names = 'image', 'x1', 'y1', 'x2', 'y2', 'class', 'image_width', 'image_height'  # column names
-  for d in 'annotations_train.csv', 'annotations_val.csv', 'annotations_test.csv':
-      x = pd.read_csv(dir / 'annotations' / d, names=names).values  # annotations
-      images, unique_images = x[:, 0], np.unique(x[:, 0])
-      with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') as f:
-          f.writelines(f'./images/{s}\n' for s in unique_images)
-      for im in tqdm(unique_images, desc=f'Converting {dir / d}'):
-          cls = 0  # single-class dataset
-          with open((dir / 'labels' / im).with_suffix('.txt'), 'a') as f:
-              for r in x[images == im]:
-                  w, h = r[6], r[7]  # image width, height
-                  xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0]  # instance
-                  f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n")  # write label

src/Guide_stick_system/image_recognition/data/VOC.yaml

@@ -1,80 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC
-# Example usage: python train.py --data VOC.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── VOC  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/VOC
-train: # train images (relative to 'path')  16551 images
-  - images/train2012
-  - images/train2007
-  - images/val2012
-  - images/val2007
-val: # val images (relative to 'path')  4952 images
-  - images/test2007
-test: # test images (optional)
-  - images/test2007
-
-# Classes
-nc: 20  # number of classes
-names: ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
-        'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor']  # class names
-
-
-# Download script/URL (optional) ---------------------------------------------------------------------------------------
-download: |
-  import xml.etree.ElementTree as ET
-
-  from tqdm import tqdm
-  from utils.general import download, Path
-
-
-  def convert_label(path, lb_path, year, image_id):
-      def convert_box(size, box):
-          dw, dh = 1. / size[0], 1. / size[1]
-          x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
-          return x * dw, y * dh, w * dw, h * dh
-
-      in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
-      out_file = open(lb_path, 'w')
-      tree = ET.parse(in_file)
-      root = tree.getroot()
-      size = root.find('size')
-      w = int(size.find('width').text)
-      h = int(size.find('height').text)
-
-      for obj in root.iter('object'):
-          cls = obj.find('name').text
-          if cls in yaml['names'] and not int(obj.find('difficult').text) == 1:
-              xmlbox = obj.find('bndbox')
-              bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ('xmin', 'xmax', 'ymin', 'ymax')])
-              cls_id = yaml['names'].index(cls)  # class id
-              out_file.write(" ".join([str(a) for a in (cls_id, *bb)]) + '\n')
-
-
-  # Download
-  dir = Path(yaml['path'])  # dataset root dir
-  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
-  urls = [url + 'VOCtrainval_06-Nov-2007.zip',  # 446MB, 5012 images
-          url + 'VOCtest_06-Nov-2007.zip',  # 438MB, 4953 images
-          url + 'VOCtrainval_11-May-2012.zip']  # 1.95GB, 17126 images
-  download(urls, dir=dir / 'images', delete=False)
-
-  # Convert
-  path = dir / f'images/VOCdevkit'
-  for year, image_set in ('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test'):
-      imgs_path = dir / 'images' / f'{image_set}{year}'
-      lbs_path = dir / 'labels' / f'{image_set}{year}'
-      imgs_path.mkdir(exist_ok=True, parents=True)
-      lbs_path.mkdir(exist_ok=True, parents=True)
-
-      image_ids = open(path / f'VOC{year}/ImageSets/Main/{image_set}.txt').read().strip().split()
-      for id in tqdm(image_ids, desc=f'{image_set}{year}'):
-          f = path / f'VOC{year}/JPEGImages/{id}.jpg'  # old img path
-          lb_path = (lbs_path / f.name).with_suffix('.txt')  # new label path
-          f.rename(imgs_path / f.name)  # move image
-          convert_label(path, lb_path, year, id)  # convert labels to YOLO format

src/Guide_stick_system/image_recognition/data/VisDrone.yaml

@@ -1,61 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset
-# Example usage: python train.py --data VisDrone.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── VisDrone  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/VisDrone  # dataset root dir
-train: VisDrone2019-DET-train/images  # train images (relative to 'path')  6471 images
-val: VisDrone2019-DET-val/images  # val images (relative to 'path')  548 images
-test: VisDrone2019-DET-test-dev/images  # test images (optional)  1610 images
-
-# Classes
-nc: 10  # number of classes
-names: ['pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor']
-
-
-# Download script/URL (optional) ---------------------------------------------------------------------------------------
-download: |
-  from utils.general import download, os, Path
-
-  def visdrone2yolo(dir):
-      from PIL import Image
-      from tqdm import tqdm
-
-      def convert_box(size, box):
-          # Convert VisDrone box to YOLO xywh box
-          dw = 1. / size[0]
-          dh = 1. / size[1]
-          return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh
-
-      (dir / 'labels').mkdir(parents=True, exist_ok=True)  # make labels directory
-      pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
-      for f in pbar:
-          img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
-          lines = []
-          with open(f, 'r') as file:  # read annotation.txt
-              for row in [x.split(',') for x in file.read().strip().splitlines()]:
-                  if row[4] == '0':  # VisDrone 'ignored regions' class 0
-                      continue
-                  cls = int(row[5]) - 1
-                  box = convert_box(img_size, tuple(map(int, row[:4])))
-                  lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
-                  with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl:
-                      fl.writelines(lines)  # write label.txt
-
-
-  # Download
-  dir = Path(yaml['path'])  # dataset root dir
-  urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip']
-  download(urls, dir=dir)
-
-  # Convert
-  for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
-      visdrone2yolo(dir / d)  # convert VisDrone annotations to YOLO labels

src/Guide_stick_system/image_recognition/data/coco.yaml

@@ -1,44 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# COCO 2017 dataset http://cocodataset.org
-# Example usage: python train.py --data coco.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── coco  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/coco  # dataset root dir
-train: train2017.txt  # train images (relative to 'path') 118287 images
-val: val2017.txt  # train images (relative to 'path') 5000 images
-test: test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
-
-# Classes
-nc: 80  # number of classes
-names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
-        'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
-        'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
-        'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
-        'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
-        'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
-        'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
-        'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
-        'hair drier', 'toothbrush']  # class names
-
-
-# Download script/URL (optional)
-download: |
-  from utils.general import download, Path
-
-  # Download labels
-  segments = False  # segment or box labels
-  dir = Path(yaml['path'])  # dataset root dir
-  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
-  urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')]  # labels
-  download(urls, dir=dir.parent)
-
-  # Download data
-  urls = ['http://images.cocodataset.org/zips/train2017.zip',  # 19G, 118k images
-          'http://images.cocodataset.org/zips/val2017.zip',  # 1G, 5k images
-          'http://images.cocodataset.org/zips/test2017.zip']  # 7G, 41k images (optional)
-  download(urls, dir=dir / 'images', threads=3)

src/Guide_stick_system/image_recognition/data/coco128.yaml

@@ -1,30 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017)
-# Example usage: python train.py --data coco128.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── coco128  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/coco128  # dataset root dir
-train: images/train2017  # train images (relative to 'path') 128 images
-val: images/train2017  # val images (relative to 'path') 128 images
-test:  # test images (optional)
-
-# Classes
-nc: 80  # number of classes
-names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
-        'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
-        'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
-        'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
-        'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
-        'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
-        'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
-        'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
-        'hair drier', 'toothbrush']  # class names
-
-
-# Download script/URL (optional)
-download: https://ultralytics.com/assets/coco128.zip

src/Guide_stick_system/image_recognition/data/data.yaml

@@ -1,13 +0,0 @@
-# Custom data for safety helmet
-
-
-# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
-train: /home/data/yolo_format/images/train
-val: /home/data/yolo_format/images/val
-
-# number of classes
-nc: 2
-
-# class names
-names: ['phone', 'person']
- 

src/Guide_stick_system/image_recognition/data/hyps/hyp.finetune.yaml

@@ -1,39 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Hyperparameters for VOC finetuning
-# python train.py --batch 64 --weights yolov5m.pt --data VOC.yaml --img 512 --epochs 50
-# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
-
-# Hyperparameter Evolution Results
-# Generations: 306
-#                   P         R     mAP.5 mAP.5:.95       box       obj       cls
-# Metrics:        0.6     0.936     0.896     0.684    0.0115   0.00805   0.00146
-
-lr0: 0.0032
-lrf: 0.12
-momentum: 0.843
-weight_decay: 0.00036
-warmup_epochs: 2.0
-warmup_momentum: 0.5
-warmup_bias_lr: 0.05
-box: 0.0296
-cls: 0.243
-cls_pw: 0.631
-obj: 0.301
-obj_pw: 0.911
-iou_t: 0.2
-anchor_t: 2.91
-# anchors: 3.63
-fl_gamma: 0.0
-hsv_h: 0.0138
-hsv_s: 0.664
-hsv_v: 0.464
-degrees: 0.373
-translate: 0.245
-scale: 0.898
-shear: 0.602
-perspective: 0.0
-flipud: 0.00856
-fliplr: 0.5
-mosaic: 1.0
-mixup: 0.243
-copy_paste: 0.0

src/Guide_stick_system/image_recognition/data/hyps/hyp.finetune_objects365.yaml

@@ -1,31 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-lr0: 0.00258
-lrf: 0.17
-momentum: 0.779
-weight_decay: 0.00058
-warmup_epochs: 1.33
-warmup_momentum: 0.86
-warmup_bias_lr: 0.0711
-box: 0.0539
-cls: 0.299
-cls_pw: 0.825
-obj: 0.632
-obj_pw: 1.0
-iou_t: 0.2
-anchor_t: 3.44
-anchors: 3.2
-fl_gamma: 0.0
-hsv_h: 0.0188
-hsv_s: 0.704
-hsv_v: 0.36
-degrees: 0.0
-translate: 0.0902
-scale: 0.491
-shear: 0.0
-perspective: 0.0
-flipud: 0.0
-fliplr: 0.5
-mosaic: 1.0
-mixup: 0.0
-copy_paste: 0.0

src/Guide_stick_system/image_recognition/data/hyps/hyp.scratch-high.yaml

@@ -1,34 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Hyperparameters for high-augmentation COCO training from scratch
-# python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300
-# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
-
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.2  # final OneCycleLR learning rate (lr0 * lrf)
-momentum: 0.937  # SGD momentum/Adam beta1
-weight_decay: 0.0005  # optimizer weight decay 5e-4
-warmup_epochs: 3.0  # warmup epochs (fractions ok)
-warmup_momentum: 0.8  # warmup initial momentum
-warmup_bias_lr: 0.1  # warmup initial bias lr
-box: 0.05  # box loss gain
-cls: 0.3  # cls loss gain
-cls_pw: 1.0  # cls BCELoss positive_weight
-obj: 0.7  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
-# anchors: 3  # anchors per output layer (0 to ignore)
-fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
-hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
-hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
-hsv_v: 0.4  # image HSV-Value augmentation (fraction)
-degrees: 0.0  # image rotation (+/- deg)
-translate: 0.1  # image translation (+/- fraction)
-scale: 0.9  # image scale (+/- gain)
-shear: 0.0  # image shear (+/- deg)
-perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
-flipud: 0.0  # image flip up-down (probability)
-fliplr: 0.5  # image flip left-right (probability)
-mosaic: 1.0  # image mosaic (probability)
-mixup: 0.1  # image mixup (probability)
-copy_paste: 0.1  # segment copy-paste (probability)

src/Guide_stick_system/image_recognition/data/hyps/hyp.scratch-low.yaml

@@ -1,34 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Hyperparameters for low-augmentation COCO training from scratch
-# python train.py --batch 64 --cfg yolov5n6.yaml --weights '' --data coco.yaml --img 640 --epochs 300 --linear
-# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
-
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.01  # final OneCycleLR learning rate (lr0 * lrf)
-momentum: 0.937  # SGD momentum/Adam beta1
-weight_decay: 0.0005  # optimizer weight decay 5e-4
-warmup_epochs: 3.0  # warmup epochs (fractions ok)
-warmup_momentum: 0.8  # warmup initial momentum
-warmup_bias_lr: 0.1  # warmup initial bias lr
-box: 0.05  # box loss gain
-cls: 0.5  # cls loss gain
-cls_pw: 1.0  # cls BCELoss positive_weight
-obj: 1.0  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
-# anchors: 3  # anchors per output layer (0 to ignore)
-fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
-hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
-hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
-hsv_v: 0.4  # image HSV-Value augmentation (fraction)
-degrees: 0.0  # image rotation (+/- deg)
-translate: 0.1  # image translation (+/- fraction)
-scale: 0.5  # image scale (+/- gain)
-shear: 0.0  # image shear (+/- deg)
-perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
-flipud: 0.0  # image flip up-down (probability)
-fliplr: 0.5  # image flip left-right (probability)
-mosaic: 1.0  # image mosaic (probability)
-mixup: 0.0  # image mixup (probability)
-copy_paste: 0.0  # segment copy-paste (probability)

src/Guide_stick_system/image_recognition/data/hyps/hyp.scratch-med.yaml

@@ -1,34 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Hyperparameters for medium-augmentation COCO training from scratch
-# python train.py --batch 32 --cfg yolov5m6.yaml --weights '' --data coco.yaml --img 1280 --epochs 300
-# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
-
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.1  # final OneCycleLR learning rate (lr0 * lrf)
-momentum: 0.937  # SGD momentum/Adam beta1
-weight_decay: 0.0005  # optimizer weight decay 5e-4
-warmup_epochs: 3.0  # warmup epochs (fractions ok)
-warmup_momentum: 0.8  # warmup initial momentum
-warmup_bias_lr: 0.1  # warmup initial bias lr
-box: 0.05  # box loss gain
-cls: 0.3  # cls loss gain
-cls_pw: 1.0  # cls BCELoss positive_weight
-obj: 0.7  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
-# anchors: 3  # anchors per output layer (0 to ignore)
-fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
-hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
-hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
-hsv_v: 0.4  # image HSV-Value augmentation (fraction)
-degrees: 0.0  # image rotation (+/- deg)
-translate: 0.1  # image translation (+/- fraction)
-scale: 0.9  # image scale (+/- gain)
-shear: 0.0  # image shear (+/- deg)
-perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
-flipud: 0.0  # image flip up-down (probability)
-fliplr: 0.5  # image flip left-right (probability)
-mosaic: 1.0  # image mosaic (probability)
-mixup: 0.1  # image mixup (probability)
-copy_paste: 0.0  # segment copy-paste (probability)

src/Guide_stick_system/image_recognition/data/hyps/hyp.scratch.yaml

@@ -1,34 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Hyperparameters for COCO training from scratch
-# python train.py --batch 40 --cfg yolov5m.yaml --weights '' --data coco.yaml --img 640 --epochs 300
-# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
-
-lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
-lrf: 0.1  # final OneCycleLR learning rate (lr0 * lrf)
-momentum: 0.937  # SGD momentum/Adam beta1
-weight_decay: 0.0005  # optimizer weight decay 5e-4
-warmup_epochs: 3.0  # warmup epochs (fractions ok)
-warmup_momentum: 0.8  # warmup initial momentum
-warmup_bias_lr: 0.1  # warmup initial bias lr
-box: 0.05  # box loss gain
-cls: 0.5  # cls loss gain
-cls_pw: 1.0  # cls BCELoss positive_weight
-obj: 1.0  # obj loss gain (scale with pixels)
-obj_pw: 1.0  # obj BCELoss positive_weight
-iou_t: 0.20  # IoU training threshold
-anchor_t: 4.0  # anchor-multiple threshold
-# anchors: 3  # anchors per output layer (0 to ignore)
-fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
-hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
-hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
-hsv_v: 0.4  # image HSV-Value augmentation (fraction)
-degrees: 0.0  # image rotation (+/- deg)
-translate: 0.1  # image translation (+/- fraction)
-scale: 0.5  # image scale (+/- gain)
-shear: 0.0  # image shear (+/- deg)
-perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
-flipud: 0.0  # image flip up-down (probability)
-fliplr: 0.5  # image flip left-right (probability)
-mosaic: 1.0  # image mosaic (probability)
-mixup: 0.0  # image mixup (probability)
-copy_paste: 0.0  # segment copy-paste (probability)

src/Guide_stick_system/image_recognition/data/mask_data.yaml

@@ -1,12 +0,0 @@
-# Custom data for safety helmet
-
-
-# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
-train: F:/up/1212/YOLO_Mask/score/images/train
-val: F:/up/1212/YOLO_Mask/score/images/val
-
-# number of classes
-nc: 2
-
-# class names
-names: ['mask', 'face']

src/Guide_stick_system/image_recognition/data/scripts/download_weights.sh

@@ -1,20 +0,0 @@
-#!/bin/bash
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Download latest models from https://github.com/ultralytics/yolov5/releases
-# Example usage: bash path/to/download_weights.sh
-# parent
-# └── yolov5
-#     ├── yolov5s.pt  ← downloads here
-#     ├── yolov5m.pt
-#     └── ...
-
-python - <<EOF
-from utils.downloads import attempt_download
-
-models = ['n', 's', 'm', 'l', 'x']
-models.extend([x + '6' for x in models])  # add P6 models
-
-for x in models:
-    attempt_download(f'yolov5{x}.pt')
-
-EOF

src/Guide_stick_system/image_recognition/data/scripts/get_coco.sh

@@ -1,27 +0,0 @@
-#!/bin/bash
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Download COCO 2017 dataset http://cocodataset.org
-# Example usage: bash data/scripts/get_coco.sh
-# parent
-# ├── yolov5
-# └── datasets
-#     └── coco  ← downloads here
-
-# Download/unzip labels
-d='../datasets' # unzip directory
-url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
-f='coco2017labels.zip' # or 'coco2017labels-segments.zip', 68 MB
-echo 'Downloading' $url$f ' ...'
-curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &
-
-# Download/unzip images
-d='../datasets/coco/images' # unzip directory
-url=http://images.cocodataset.org/zips/
-f1='train2017.zip' # 19G, 118k images
-f2='val2017.zip'   # 1G, 5k images
-f3='test2017.zip'  # 7G, 41k images (optional)
-for f in $f1 $f2; do
-  echo 'Downloading' $url$f '...'
-  curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &
-done
-wait # finish background tasks

src/Guide_stick_system/image_recognition/data/scripts/get_coco128.sh

@@ -1,17 +0,0 @@
-#!/bin/bash
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Download COCO128 dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017)
-# Example usage: bash data/scripts/get_coco128.sh
-# parent
-# ├── yolov5
-# └── datasets
-#     └── coco128  ← downloads here
-
-# Download/unzip images and labels
-d='../datasets' # unzip directory
-url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
-f='coco128.zip' # or 'coco128-segments.zip', 68 MB
-echo 'Downloading' $url$f ' ...'
-curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &
-
-wait # finish background tasks

src/Guide_stick_system/image_recognition/data/xView.yaml

@@ -1,102 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# xView 2018 dataset https://challenge.xviewdataset.org
-# --------  DOWNLOAD DATA MANUALLY from URL above and unzip to 'datasets/xView' before running train command!  --------
-# Example usage: python train.py --data xView.yaml
-# parent
-# ├── yolov5
-# └── datasets
-#     └── xView  ← downloads here
-
-
-# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
-path: ../datasets/xView  # dataset root dir
-train: images/autosplit_train.txt  # train images (relative to 'path') 90% of 847 train images
-val: images/autosplit_val.txt  # train images (relative to 'path') 10% of 847 train images
-
-# Classes
-nc: 60  # number of classes
-names: ['Fixed-wing Aircraft', 'Small Aircraft', 'Cargo Plane', 'Helicopter', 'Passenger Vehicle', 'Small Car', 'Bus',
-        'Pickup Truck', 'Utility Truck', 'Truck', 'Cargo Truck', 'Truck w/Box', 'Truck Tractor', 'Trailer',
-        'Truck w/Flatbed', 'Truck w/Liquid', 'Crane Truck', 'Railway Vehicle', 'Passenger Car', 'Cargo Car',
-        'Flat Car', 'Tank car', 'Locomotive', 'Maritime Vessel', 'Motorboat', 'Sailboat', 'Tugboat', 'Barge',
-        'Fishing Vessel', 'Ferry', 'Yacht', 'Container Ship', 'Oil Tanker', 'Engineering Vehicle', 'Tower crane',
-        'Container Crane', 'Reach Stacker', 'Straddle Carrier', 'Mobile Crane', 'Dump Truck', 'Haul Truck',
-        'Scraper/Tractor', 'Front loader/Bulldozer', 'Excavator', 'Cement Mixer', 'Ground Grader', 'Hut/Tent', 'Shed',
-        'Building', 'Aircraft Hangar', 'Damaged Building', 'Facility', 'Construction Site', 'Vehicle Lot', 'Helipad',
-        'Storage Tank', 'Shipping container lot', 'Shipping Container', 'Pylon', 'Tower']  # class names
-
-
-# Download script/URL (optional) ---------------------------------------------------------------------------------------
-download: |
-  import json
-  import os
-  from pathlib import Path
-
-  import numpy as np
-  from PIL import Image
-  from tqdm import tqdm
-
-  from utils.datasets import autosplit
-  from utils.general import download, xyxy2xywhn
-
-
-  def convert_labels(fname=Path('xView/xView_train.geojson')):
-      # Convert xView geoJSON labels to YOLO format
-      path = fname.parent
-      with open(fname) as f:
-          print(f'Loading {fname}...')
-          data = json.load(f)
-
-      # Make dirs
-      labels = Path(path / 'labels' / 'train')
-      os.system(f'rm -rf {labels}')
-      labels.mkdir(parents=True, exist_ok=True)
-
-      # xView classes 11-94 to 0-59
-      xview_class2index = [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, -1, 9, 10, 11,
-                           12, 13, 14, 15, -1, -1, 16, 17, 18, 19, 20, 21, 22, -1, 23, 24, 25, -1, 26, 27, -1, 28, -1,
-                           29, 30, 31, 32, 33, 34, 35, 36, 37, -1, 38, 39, 40, 41, 42, 43, 44, 45, -1, -1, -1, -1, 46,
-                           47, 48, 49, -1, 50, 51, -1, 52, -1, -1, -1, 53, 54, -1, 55, -1, -1, 56, -1, 57, -1, 58, 59]
-
-      shapes = {}
-      for feature in tqdm(data['features'], desc=f'Converting {fname}'):
-          p = feature['properties']
-          if p['bounds_imcoords']:
-              id = p['image_id']
-              file = path / 'train_images' / id
-              if file.exists():  # 1395.tif missing
-                  try:
-                      box = np.array([int(num) for num in p['bounds_imcoords'].split(",")])
-                      assert box.shape[0] == 4, f'incorrect box shape {box.shape[0]}'
-                      cls = p['type_id']
-                      cls = xview_class2index[int(cls)]  # xView class to 0-60
-                      assert 59 >= cls >= 0, f'incorrect class index {cls}'
-
-                      # Write YOLO label
-                      if id not in shapes:
-                          shapes[id] = Image.open(file).size
-                      box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True)
-                      with open((labels / id).with_suffix('.txt'), 'a') as f:
-                          f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n")  # write label.txt
-                  except Exception as e:
-                      print(f'WARNING: skipping one label for {file}: {e}')
-
-
-  # Download manually from https://challenge.xviewdataset.org
-  dir = Path(yaml['path'])  # dataset root dir
-  # urls = ['https://d307kc0mrhucc3.cloudfront.net/train_labels.zip',  # train labels
-  #         'https://d307kc0mrhucc3.cloudfront.net/train_images.zip',  # 15G, 847 train images
-  #         'https://d307kc0mrhucc3.cloudfront.net/val_images.zip']  # 5G, 282 val images (no labels)
-  # download(urls, dir=dir, delete=False)
-
-  # Convert labels
-  convert_labels(dir / 'xView_train.geojson')
-
-  # Move images
-  images = Path(dir / 'images')
-  images.mkdir(parents=True, exist_ok=True)
-  Path(dir / 'train_images').rename(dir / 'images' / 'train')
-  Path(dir / 'val_images').rename(dir / 'images' / 'val')
-
-  # Split
-  autosplit(dir / 'images' / 'train')

src/Guide_stick_system/image_recognition/data_gen.py

@@ -1,236 +0,0 @@
-# -*- coding: utf-8 -*-
-"""
--------------------------------------------------
-Project Name: yolov5-jishi
-File Name: data_gen.py
-Author: chenming
-Create Date: 2021/11/8
-Description：
--------------------------------------------------
-"""
-# -*- coding: utf-8 -*-
-# @Time    : 20210610
-# @Author  : dejahu
-# @File    : gen_yolo_data.py
-# @Software: PyCharm
-# @Brief   : 生成测试、验证、训练的图片和标签
-
-import os
-import shutil
-from pathlib import Path
-from shutil import copyfile
- 
-import cv2
-from PIL import Image, ImageDraw
-from xml.dom.minidom import parse
-import numpy as np
-import os.path as osp
-import random
-
-# main，首先在当前目录生成数据的划分
-
-# 开始转化数据集
-
-# 更换代码中images替换的逻辑，和文件对应起来
-
-# todo 修改为你的数据的根目录
-FILE_ROOT = "/scm/data/xianyu/Mask/"
-IMAGE_SET_ROOT = FILE_ROOT + "VOC2021_Mask/ImageSets/Main"   # 图片区分文件的路径
-IMAGE_PATH = FILE_ROOT + "VOC2021_Mask/JPEGImages"  # 图片的位置
-ANNOTATIONS_PATH = FILE_ROOT + "VOC2021_Mask/Annotations"  # 数据集标签文件的位置
-LABELS_ROOT = FILE_ROOT + "VOC2021_Mask/Labels"  # 进行归一化之后的标签位置
-DEST_PPP = FILE_ROOT + "mask_yolo_format"
-DEST_IMAGES_PATH = "mask_yolo_format/images"  # 区分训练集、测试集、验证集的图片目标路径
-DEST_LABELS_PATH = "mask_yolo_format/labels"  # 区分训练集、测试集、验证集的标签文件目标路径
-
-if osp.isdir(LABELS_ROOT):
-    shutil.rmtree(LABELS_ROOT)
-    print("Labels存在，已删除")
-
-if osp.isdir(DEST_PPP):
-    shutil.rmtree(DEST_PPP)
-    print("Dest目录存在，已删除")
-# todo 修改为你数据集的标签名称
-label_names = ['face', 'face_mask']
-
-
-def cord_converter(size, box):
-    """
-    将标注的 xml 文件标注转换为 darknet 形的坐标
-    :param size: 图片的尺寸： [w,h]
-    :param box: anchor box 的坐标 [左上角x,左上角y,右下角x,右下角y,]
-    :return: 转换后的 [x,y,w,h]
-    """
-    x1 = int(box[0])
-    y1 = int(box[1])
-    x2 = int(box[2])
-    y2 = int(box[3])
-
-    dw = np.float32(1. / int(size[0]))
-    dh = np.float32(1. / int(size[1]))
-
-    w = x2 - x1
-    h = y2 - y1
-    x = x1 + (w / 2)
-    y = y1 + (h / 2)
-
-    x = x * dw
-    w = w * dw
-    y = y * dh
-    h = h * dh
-    return [x, y, w, h]
-
-
-def save_file(img_jpg_file_name, size, img_box):
-    # print("保存图片")
-    save_file_name = LABELS_ROOT + '/' + img_jpg_file_name + '.txt'
-    # print(save_file_name)
-    file_path = open(save_file_name, "a+")
-    # 默认给定的是id为0，防止错误数据的出现
-    for box in img_box:
-        box_name = box[0]
-        cls_num = 0
-        if box_name in label_names:
-            cls_num = label_names.index(box_name)
-        new_box = cord_converter(size, box[1:])
-        file_path.write(f"{cls_num} {new_box[0]} {new_box[1]} {new_box[2]} {new_box[3]}\n")
-    file_path.flush()
-    file_path.close()
-
-
-def test_dataset_box_feature(file_name, point_array):
-    """
-    使用样本数据测试数据集的建议框
-    :param image_name: 图片文件名
-    :param point_array: 全部的点 [建议框sx1,sy1,sx2,sy2]
-    :return: None
-    """
-    im = Image.open(rf"{IMAGE_PATH}\{file_name}")
-    imDraw = ImageDraw.Draw(im)
-    for box in point_array:
-        x1 = box[1]
-        y1 = box[2]
-        x2 = box[3]
-        y2 = box[4]
-        imDraw.rectangle((x1, y1, x2, y2), outline='red')
-    im.show()
-
-
-def get_xml_data(file_path, img_xml_file):
-    img_path = file_path + '/' + img_xml_file + '.xml'
-    # print(img_path)
-    dom = parse(img_path)
-    root = dom.documentElement
-    img_name = root.getElementsByTagName("filename")[0].childNodes[0].data
-    img_jpg_file_name = img_xml_file + '.jpg'
-    # print(img_jpg_file_name)
-    cv2.imread(img_jpg_file_name)
-    img_size = root.getElementsByTagName("size")[0]
-    if len(img_size) == 0:
-        img_h, img_w, c = cv2.imread(img_jpg_file_name).shape
-    else:
-        img_w = img_size.getElementsByTagName("width")[0].childNodes[0].data
-        img_h = img_size.getElementsByTagName("height")[0].childNodes[0].data
-        img_c = img_size.getElementsByTagName("depth")[0].childNodes[0].data
-    objects = root.getElementsByTagName("object")
-
-    img_box = []
-    for box in objects:
-        cls_name = box.getElementsByTagName("name")[0].childNodes[0].data
-        # todo 更换坐标点转换的逻辑
-        x1 = int(float(box.getElementsByTagName("xmin")[0].childNodes[0].data))
-        y1 = int(float(box.getElementsByTagName("ymin")[0].childNodes[0].data))
-        x2 = int(float(box.getElementsByTagName("xmax")[0].childNodes[0].data))
-        y2 = int(float(box.getElementsByTagName("ymax")[0].childNodes[0].data))
-        # print("box:(c,xmin,ymin,xmax,ymax)", cls_name, x1, y1, x2, y2)
-
-        img_box.append([cls_name, x1, y1, x2, y2])
-    # test_dataset_box_feature(img_jpg_file_name, img_box)
-    save_file(img_xml_file, [img_w, img_h], img_box)
-
-
-def copy_data(img_set_source, img_labels_root, imgs_source, type):
-    file_name = img_set_source + '/' + type + ".txt"
-    file = open(file_name)
-
-    # 判断文件夹是否存在，不存在则创建
-    root_file = Path(FILE_ROOT + DEST_IMAGES_PATH + '/' + type)
-    if not root_file.exists():
-        print(f"Path {root_file} is not exit")
-        os.makedirs(root_file)
-
-    root_file = Path(FILE_ROOT + DEST_LABELS_PATH + '/' + type)
-    if not root_file.exists():
-        print(f"Path {root_file} is not exit")
-        os.makedirs(root_file)
-
-    # 遍历文件夹
-    for line in file.readlines():
-        # print(line)
-        img_name = line.strip('\n')
-        img_sor_file = imgs_source + '/' + img_name + '.jpg'
-        label_sor_file = img_labels_root + '/' + img_name + '.txt'
-
-        # 复制图片
-        DICT_DIR = FILE_ROOT + DEST_IMAGES_PATH + '/' + type
-        img_dict_file = DICT_DIR + '/' + img_name + '.jpg'
-        copyfile(img_sor_file, img_dict_file)
-
-        # 复制 label
-        DICT_DIR = FILE_ROOT + DEST_LABELS_PATH + '/' + type
-        img_dict_file = DICT_DIR + '/' + img_name + '.txt'
-        copyfile(label_sor_file, img_dict_file)
-
-
-if __name__ == '__main__':
-    # 将文件进行 train 和 val 的区分
-    # 用于生成测试集使用，目前还在测试阶段，暂时不发布
-    img_set_root = IMAGE_SET_ROOT
-    imgs_root = IMAGE_PATH
-    img_labels_root = LABELS_ROOT
-    if osp.isdir(img_labels_root) == False:
-        os.makedirs(img_labels_root)
-    os.makedirs(DEST_PPP)
-    names = os.listdir(ANNOTATIONS_PATH)
-    # real_names = []
-    # for name in names:
-    #     if name.split(".")[-1] == "xml":
-    #         real_names.append(name.split(".")[0])
-    # # print(real_names)
-    # # print(real_names)
-    # random.shuffle(real_names)
-    # # print(real_names)
-    # length = len(real_names)
-    # split_point = int(length * 0.2)
-    #
-    # val_names = real_names[:split_point]
-    # train_names = real_names[split_point:]
-    #
-    # # 开始生成文件
-    # np.savetxt('data/val.txt', np.array(val_names), fmt="%s", delimiter="\n")
-    # np.savetxt('data/test.txt', np.array(val_names), fmt="%s", delimiter="\n")
-    # np.savetxt('data/train.txt', np.array(train_names), fmt="%s", delimiter="\n")
-    # print("txt文件生成完毕，请放在VOC2012的ImageSets/Main的目录下")
-    # 生成标签
-    root = ANNOTATIONS_PATH
-    files_all = os.listdir(root)
-    files = []
-    for file in files_all:
-        if file.split(".")[-1] == "xml":
-            files.append(file.split(".")[0])
-    # print(len(files))
-    for file in files:
-        # print("file name: ", file)
-        file_xml = file.split(".")
-        # try:
-        get_xml_data(root, file_xml[0])
-        # except:
-        #     print(file_xml[0])
-        # break
-    # copy_data(img_set_root, img_labels_root, imgs_root, "train")
-    # copy_data(img_set_root, img_labels_root, imgs_root, "val")
-    # copy_data(img_set_root, img_labels_root, imgs_root, "test")
-    # data = list(np.loadtxt("tt100k.txt", dtype=str))
-    # print(data)
-    # print(len(data))
-    print("数据转换已完成！")

src/Guide_stick_system/image_recognition/detect.py

@@ -1,246 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Run inference on images, videos, directories, streams, etc.
-
-Usage:
-    $ python path/to/detect.py --weights yolov5s.pt --source 0  # webcam
-                                                             img.jpg  # image
-                                                             vid.mp4  # video
-                                                             path/  # directory
-                                                             path/*.jpg  # glob
-                                                             'https://youtu.be/Zgi9g1ksQHc'  # YouTube
-                                                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
-"""
-
-import argparse
-import os
-import sys 
-from pathlib import Path
-
-import cv2
-import torch
-import torch.backends.cudnn as cudnn
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[0]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
-
-from models.common import DetectMultiBackend
-from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
-from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
-                           increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
-from utils.plots import Annotator, colors, save_one_box
-from utils.torch_utils import select_device, time_sync
-
-
-@torch.no_grad()
-def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
-        source=ROOT / 'data/images',  # file/dir/URL/glob, 0 for webcam
-        imgsz=640,  # inference size (pixels)
-        conf_thres=0.25,  # confidence threshold
-        iou_thres=0.45,  # NMS IOU threshold
-        max_det=1000,  # maximum detections per image
-        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
-        view_img=False,  # show results
-        save_txt=False,  # save results to *.txt
-        save_conf=False,  # save confidences in --save-txt labels
-        save_crop=False,  # save cropped prediction boxes
-        nosave=False,  # do not save images/videos
-        classes=None,  # filter by class: --class 0, or --class 0 2 3
-        agnostic_nms=False,  # class-agnostic NMS
-        augment=False,  # augmented inference
-        visualize=False,  # visualize features
-        update=False,  # update all models
-        project=ROOT / 'runs/detect',  # save results to project/name
-        name='exp',  # save results to project/name
-        exist_ok=False,  # existing project/name ok, do not increment
-        line_thickness=3,  # bounding box thickness (pixels)
-        hide_labels=False,  # hide labels
-        hide_conf=False,  # hide confidences
-        half=False,  # use FP16 half-precision inference
-        dnn=False,  # use OpenCV DNN for ONNX inference
-        ):
-    source = str(source)
-    save_img = not nosave and not source.endswith('.txt')  # save inference images
-    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
-    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
-    if is_url and is_file:
-        source = check_file(source)  # download
-
-    # Directories
-    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
-    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
-
-    # Load model
-    device = select_device(device)
-    model = DetectMultiBackend(weights, device=device, dnn=dnn)
-    stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx
-    imgsz = check_img_size(imgsz, s=stride)  # check image size
-
-    # Half
-    half &= pt and device.type != 'cpu'  # half precision only supported by PyTorch on CUDA
-    if pt:
-        model.model.half() if half else model.model.float()
-
-    # Dataloader
-    if webcam:
-        view_img = check_imshow()
-        cudnn.benchmark = True  # set True to speed up constant image size inference
-        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt and not jit)
-        bs = len(dataset)  # batch_size
-    else:
-        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt and not jit)
-        bs = 1  # batch_size
-    vid_path, vid_writer = [None] * bs, [None] * bs
-
-    # Run inference
-    if pt and device.type != 'cpu':
-        model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.model.parameters())))  # warmup
-    dt, seen = [0.0, 0.0, 0.0], 0
-    for path, im, im0s, vid_cap, s in dataset:
-        t1 = time_sync()
-        im = torch.from_numpy(im).to(device)
-        im = im.half() if half else im.float()  # uint8 to fp16/32
-        im /= 255  # 0 - 255 to 0.0 - 1.0
-        if len(im.shape) == 3:
-            im = im[None]  # expand for batch dim
-        t2 = time_sync()
-        dt[0] += t2 - t1
-
-        # Inference
-        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
-        pred = model(im, augment=augment, visualize=visualize)
-        t3 = time_sync()
-        dt[1] += t3 - t2
-
-        # NMS
-        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
-        dt[2] += time_sync() - t3
-
-        # Second-stage classifier (optional)
-        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
-
-        # Process predictions
-        for i, det in enumerate(pred):  # per image
-            seen += 1
-            if webcam:  # batch_size >= 1
-                p, im0, frame = path[i], im0s[i].copy(), dataset.count
-                s += f'{i}: '
-            else:
-                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
-
-            p = Path(p)  # to Path
-            save_path = str(save_dir / p.name)  # im.jpg
-            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
-            s += '%gx%g ' % im.shape[2:]  # print string
-            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
-            imc = im0.copy() if save_crop else im0  # for save_crop
-            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
-            if len(det):
-                # Rescale boxes from img_size to im0 size
-                det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
-
-                # Print results
-                for c in det[:, -1].unique():
-                    n = (det[:, -1] == c).sum()  # detections per class
-                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
-
-                # Write results
-                for *xyxy, conf, cls in reversed(det):
-                    if save_txt:  # Write to file
-                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
-                        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
-                        with open(txt_path + '.txt', 'a') as f:
-                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
-
-                    if save_img or save_crop or view_img:  # Add bbox to image
-                        c = int(cls)  # integer class
-                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
-                        annotator.box_label(xyxy, label, color=colors(c, True))
-                        if save_crop:
-                            save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
-
-            # Print time (inference-only)
-            LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
-
-            # Stream results
-            im0 = annotator.result()
-            if view_img:
-                cv2.imshow(str(p), im0)
-                cv2.waitKey(1)  # 1 millisecond
-
-            # Save results (image with detections)
-            if save_img:
-                if dataset.mode == 'image':
-                    cv2.imwrite(save_path, im0)
-                else:  # 'video' or 'stream'
-                    if vid_path[i] != save_path:  # new video
-                        vid_path[i] = save_path
-                        if isinstance(vid_writer[i], cv2.VideoWriter):
-                            vid_writer[i].release()  # release previous video writer
-                        if vid_cap:  # video
-                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
-                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
-                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
-                        else:  # stream
-                            fps, w, h = 30, im0.shape[1], im0.shape[0]
-                            save_path += '.mp4'
-                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
-                    vid_writer[i].write(im0)
-
-    # Print results
-    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
-    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
-    if save_txt or save_img:
-        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
-        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
-    if update:
-        strip_optimizer(weights)  # update model (to fix SourceChangeWarning)
-
-
-def parse_opt():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path(s)')
-    parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam')
-    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
-    parser.add_argument('--conf-thres', type=float, default=0.5, help='confidence threshold')
-    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
-    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
-    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
-    parser.add_argument('--view-img', action='store_true', help='show results')
-    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
-    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
-    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
-    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
-    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
-    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
-    parser.add_argument('--augment', action='store_true', help='augmented inference')
-    parser.add_argument('--visualize', action='store_true', help='visualize features')
-    parser.add_argument('--update', action='store_true', help='update all models')
-    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
-    parser.add_argument('--name', default='exp', help='save results to project/name')
-    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
-    parser.add_argument('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)')
-    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
-    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
-    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
-    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
-    opt = parser.parse_args()
-    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
-    print_args(FILE.stem, opt)
-    return opt
-
-
-def main(opt):
-    check_requirements(exclude=('tensorboard', 'thop'))
-    run(**vars(opt))
-
-
-# 命令使用
-# python detect.py --weights runs/train/exp_yolov5s/weights/best.pt --source  data/images/fishman.jpg # webcam
-if __name__ == "__main__":
-    opt = parse_opt()
-    main(opt)

src/Guide_stick_system/image_recognition/docs/Dockerfile

@@ -1,61 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
-FROM nvcr.io/nvidia/pytorch:21.10-py3
-
-# Install linux packages
-RUN apt update && apt install -y zip htop screen libgl1-mesa-glx
-
-# Install python dependencies
-COPY ../requirements.txt .
-RUN python -m pip install --upgrade pip
-RUN pip uninstall -y nvidia-tensorboard nvidia-tensorboard-plugin-dlprof
-RUN pip install --no-cache -r requirements.txt coremltools onnx gsutil notebook wandb>=0.12.2
-RUN pip install --no-cache -U torch torchvision numpy Pillow
-# RUN pip install --no-cache torch==1.10.0+cu113 torchvision==0.11.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
-
-# Create working directory
-RUN mkdir -p /usr/src/app
-WORKDIR /usr/src/app
-
-# Copy contents
-COPY .. /usr/src/app
-
-# Downloads to user config dir
-ADD https://ultralytics.com/assets/Arial.ttf /root/.config/Ultralytics/
-
-# Set environment variables
-# ENV HOME=/usr/src/app
-
-
-# Usage Examples -------------------------------------------------------------------------------------------------------
-
-# Build and Push
-# t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t
-
-# Pull and Run
-# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t
-
-# Pull and Run with local directory access
-# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t
-
-# Kill all
-# sudo docker kill $(sudo docker ps -q)
-
-# Kill all image-based
-# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest)
-
-# Bash into running container
-# sudo docker exec -it 5a9b5863d93d bash
-
-# Bash into stopped container
-# id=$(sudo docker ps -qa) && sudo docker start $id && sudo docker exec -it $id bash
-
-# Clean up
-# docker system prune -a --volumes
-
-# Update Ubuntu drivers
-# https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/
-
-# DDP test
-# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3

src/Guide_stick_system/image_recognition/docs/README.md

@@ -1,292 +0,0 @@
-<div align="center">
-<p>
-   <a align="left" href="https://ultralytics.com/yolov5" target="_blank">
-   <img width="850" src="https://github.com/ultralytics/yolov5/releases/download/v1.0/splash.jpg"></a>
-</p>
-<br>
-<div>
-   <a href="https://github.com/ultralytics/yolov5/actions"><img src="https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg" alt="CI CPU testing"></a>
-   <a href="https://zenodo.org/badge/latestdoi/264818686"><img src="https://zenodo.org/badge/264818686.svg" alt="YOLOv5 Citation"></a>
-   <a href="https://hub.docker.com/r/ultralytics/yolov5"><img src="https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker" alt="Docker Pulls"></a>
-   <br>
-   <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
-   <a href="https://www.kaggle.com/ultralytics/yolov5"><img src="https://kaggle.com/static/images/open-in-kaggle.svg" alt="Open In Kaggle"></a>
-   <a href="https://join.slack.com/t/ultralytics/shared_invite/zt-w29ei8bp-jczz7QYUmDtgo6r6KcMIAg"><img src="https://img.shields.io/badge/Slack-Join_Forum-blue.svg?logo=slack" alt="Join Forum"></a>
-</div>
-<br>
-<div align="center">
-   <a href="https://github.com/ultralytics">
-   <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-github.png" width="2%"/>
-   </a>
-   <img width="2%" />
-   <a href="https://www.linkedin.com/company/ultralytics">
-   <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-linkedin.png" width="2%"/>
-   </a>
-   <img width="2%" />
-   <a href="https://twitter.com/ultralytics">
-   <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-twitter.png" width="2%"/>
-   </a>
-   <img width="2%" />
-   <a href="https://youtube.com/ultralytics">
-   <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-youtube.png" width="2%"/>
-   </a>
-   <img width="2%" />
-   <a href="https://www.facebook.com/ultralytics">
-   <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-facebook.png" width="2%"/>
-   </a>
-   <img width="2%" />
-   <a href="https://www.instagram.com/ultralytics/">
-   <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-instagram.png" width="2%"/>
-   </a>
-</div>
-
-<br>
-<p>
-YOLOv5 🚀 is a family of object detection architectures and models pretrained on the COCO dataset, and represents <a href="https://ultralytics.com">Ultralytics</a>
- open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.
-</p>
-
-<!--
-<a align="center" href="https://ultralytics.com/yolov5" target="_blank">
-<img width="800" src="https://github.com/ultralytics/yolov5/releases/download/v1.0/banner-api.png"></a>
--->
-
-</div>
-
-## <div align="center">Documentation</div>
-
-See the [YOLOv5 Docs](https://docs.ultralytics.com) for full documentation on training, testing and deployment.
-
-## <div align="center">Quick Start Examples</div>
-
-<details open>
-<summary>Install</summary>
-
-[**Python>=3.6.0**](https://www.python.org/) is required with all
-[requirements.txt](https://github.com/ultralytics/yolov5/blob/master/requirements.txt) installed including
-[**PyTorch>=1.7**](https://pytorch.org/get-started/locally/):
-<!-- $ sudo apt update && apt install -y libgl1-mesa-glx libsm6 libxext6 libxrender-dev -->
-
-```bash
-$ git clone https://github.com/ultralytics/yolov5
-$ cd yolov5
-$ pip install -r requirements.txt
-```
-
-</details>
-
-<details open>
-<summary>Inference</summary>
-
-Inference with YOLOv5 and [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36). Models automatically download
-from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases).
-
-```python
-import torch
-
-# Model
-model = torch.hub.load('ultralytics/yolov5', 'yolov5s')  # or yolov5m, yolov5l, yolov5x, custom
-
-# Images
-img = 'https://ultralytics.com/images/zidane.jpg'  # or file, Path, PIL, OpenCV, numpy, list
-
-# Inference
-results = model(img)
-
-# Results
-results.print()  # or .show(), .save(), .crop(), .pandas(), etc.
-```
-
-</details>
-
-
-
-<details>
-<summary>Inference with detect.py</summary>
-
-`detect.py` runs inference on a variety of sources, downloading models automatically from
-the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases) and saving results to `runs/detect`.
-
-```bash
-$ python detect.py --source 0  # webcam
-                            img.jpg  # image
-                            vid.mp4  # video
-                            path/  # directory
-                            path/*.jpg  # glob
-                            'https://youtu.be/Zgi9g1ksQHc'  # YouTube
-                            'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
-```
-
-</details>
-
-<details>
-<summary>Training</summary>
-
-Run commands below to reproduce results
-on [COCO](https://github.com/ultralytics/yolov5/blob/master/data/scripts/get_coco.sh) dataset (dataset auto-downloads on
-first use). Training times for YOLOv5s/m/l/x are 2/4/6/8 days on a single V100 (multi-GPU times faster). Use the
-largest `--batch-size` your GPU allows (batch sizes shown for 16 GB devices).
-
-```bash
-$ python train.py --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 64
-                                         yolov5m                                40
-                                         yolov5l                                24
-                                         yolov5x                                16
-```
-
-<img width="800" src="https://user-images.githubusercontent.com/26833433/90222759-949d8800-ddc1-11ea-9fa1-1c97eed2b963.png">
-
-</details>
-
-<details open>
-<summary>Tutorials</summary>
-
-* [Train Custom Data](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data)&nbsp; 🚀 RECOMMENDED
-* [Tips for Best Training Results](https://github.com/ultralytics/yolov5/wiki/Tips-for-Best-Training-Results)&nbsp; ☘️
-  RECOMMENDED
-* [Weights & Biases Logging](https://github.com/ultralytics/yolov5/issues/1289)&nbsp; 🌟 NEW
-* [Roboflow for Datasets, Labeling, and Active Learning](https://github.com/ultralytics/yolov5/issues/4975)&nbsp; 🌟 NEW
-* [Multi-GPU Training](https://github.com/ultralytics/yolov5/issues/475)
-* [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36)&nbsp; ⭐ NEW
-* [TorchScript, ONNX, CoreML Export](https://github.com/ultralytics/yolov5/issues/251) 🚀
-* [Test-Time Augmentation (TTA)](https://github.com/ultralytics/yolov5/issues/303)
-* [Model Ensembling](https://github.com/ultralytics/yolov5/issues/318)
-* [Model Pruning/Sparsity](https://github.com/ultralytics/yolov5/issues/304)
-* [Hyperparameter Evolution](https://github.com/ultralytics/yolov5/issues/607)
-* [Transfer Learning with Frozen Layers](https://github.com/ultralytics/yolov5/issues/1314)&nbsp; ⭐ NEW
-* [TensorRT Deployment](https://github.com/wang-xinyu/tensorrtx)
-
-</details>
-
-## <div align="center">Environments</div>
-
-Get started in seconds with our verified environments. Click each icon below for details.
-
-<div align="center">
-    <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-colab-small.png" width="15%"/>
-    </a>
-    <a href="https://www.kaggle.com/ultralytics/yolov5">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-kaggle-small.png" width="15%"/>
-    </a>
-    <a href="https://hub.docker.com/r/ultralytics/yolov5">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-docker-small.png" width="15%"/>
-    </a>
-    <a href="https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-aws-small.png" width="15%"/>
-    </a>
-    <a href="https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-gcp-small.png" width="15%"/>
-    </a>
-</div>
-
-## <div align="center">Integrations</div>
-
-<div align="center">
-    <a href="https://wandb.ai/site?utm_campaign=repo_yolo_readme">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-wb-long.png" width="49%"/>
-    </a>
-    <a href="https://roboflow.com/?ref=ultralytics">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-roboflow-long.png" width="49%"/>
-    </a>
-</div>
-
-|Weights and Biases|Roboflow ⭐ NEW|
-|:-:|:-:|
-|Automatically track and visualize all your YOLOv5 training runs in the cloud with [Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_readme)|Label and export your custom datasets directly to YOLOv5 for training with [Roboflow](https://roboflow.com/?ref=ultralytics) |
-
-
-<!-- ## <div align="center">Compete and Win</div>
-
-We are super excited about our first-ever Ultralytics YOLOv5 🚀 EXPORT Competition with **$10,000** in cash prizes!
-
-<p align="center">
-  <a href="https://github.com/ultralytics/yolov5/discussions/3213">
-  <img width="850" src="https://github.com/ultralytics/yolov5/releases/download/v1.0/banner-export-competition.png"></a>
-</p> -->
-
-## <div align="center">Why YOLOv5</div>
-
-<p align="left"><img width="800" src="https://user-images.githubusercontent.com/26833433/136901921-abcfcd9d-f978-4942-9b97-0e3f202907df.png"></p>
-<details>
-  <summary>YOLOv5-P5 640 Figure (click to expand)</summary>
-
-<p align="left"><img width="800" src="https://user-images.githubusercontent.com/26833433/136763877-b174052b-c12f-48d2-8bc4-545e3853398e.png"></p>
-</details>
-<details>
-  <summary>Figure Notes (click to expand)</summary>
-
-* **COCO AP val** denotes mAP@0.5:0.95 metric measured on the 5000-image [COCO val2017](http://cocodataset.org) dataset over various inference sizes from 256 to 1536.
-* **GPU Speed** measures average inference time per image on [COCO val2017](http://cocodataset.org) dataset using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) V100 instance at batch-size 32.
-* **EfficientDet** data from [google/automl](https://github.com/google/automl) at batch size 8.
-* **Reproduce** by `python val.py --task study --data coco.yaml --iou 0.7 --weights yolov5n6.pt yolov5s6.pt yolov5m6.pt yolov5l6.pt yolov5x6.pt`
-</details>
-
-### Pretrained Checkpoints
-
-[assets]: https://github.com/ultralytics/yolov5/releases
-[TTA]: https://github.com/ultralytics/yolov5/issues/303
-
-|Model |size<br><sup>(pixels) |mAP<sup>val<br>0.5:0.95 |mAP<sup>val<br>0.5 |Speed<br><sup>CPU b1<br>(ms) |Speed<br><sup>V100 b1<br>(ms) |Speed<br><sup>V100 b32<br>(ms) |params<br><sup>(M) |FLOPs<br><sup>@640 (B)
-|---                    |---  |---    |---    |---    |---    |---    |---    |---
-|[YOLOv5n][assets]      |640  |28.4   |46.0   |**45** |**6.3**|**0.6**|**1.9**|**4.5**
-|[YOLOv5s][assets]      |640  |37.2   |56.0   |98     |6.4    |0.9    |7.2    |16.5
-|[YOLOv5m][assets]      |640  |45.2   |63.9   |224    |8.2    |1.7    |21.2   |49.0
-|[YOLOv5l][assets]      |640  |48.8   |67.2   |430    |10.1   |2.7    |46.5   |109.1
-|[YOLOv5x][assets]      |640  |50.7   |68.9   |766    |12.1   |4.8    |86.7   |205.7
-|                       |     |       |       |       |       |       |       |
-|[YOLOv5n6][assets]     |1280 |34.0   |50.7   |153    |8.1    |2.1    |3.2    |4.6
-|[YOLOv5s6][assets]     |1280 |44.5   |63.0   |385    |8.2    |3.6    |16.8   |12.6
-|[YOLOv5m6][assets]     |1280 |51.0   |69.0   |887    |11.1   |6.8    |35.7   |50.0
-|[YOLOv5l6][assets]     |1280 |53.6   |71.6   |1784   |15.8   |10.5   |76.8   |111.4
-|[YOLOv5x6][assets]<br>+ [TTA][TTA]|1280<br>1536 |54.7<br>**55.4** |**72.4**<br>72.3 |3136<br>- |26.2<br>- |19.4<br>- |140.7<br>- |209.8<br>-
-
-<details>
-  <summary>Table Notes (click to expand)</summary>
-
-* All checkpoints are trained to 300 epochs with default settings and hyperparameters.
-* **mAP<sup>val</sup>** values are for single-model single-scale on [COCO val2017](http://cocodataset.org) dataset.<br>Reproduce by `python val.py --data coco.yaml --img 640 --conf 0.001 --iou 0.65`
-* **Speed** averaged over COCO val images using a [AWS p3.2xlarge](https://aws.amazon.com/ec2/instance-types/p3/) instance. NMS times (~1 ms/img) not included.<br>Reproduce by `python val.py --data coco.yaml --img 640 --conf 0.25 --iou 0.45`
-* **TTA** [Test Time Augmentation](https://github.com/ultralytics/yolov5/issues/303) includes reflection and scale augmentations.<br>Reproduce by `python val.py --data coco.yaml --img 1536 --iou 0.7 --augment`
-
-</details>
-
-## <div align="center">Contribute</div>
-
-We love your input! We want to make contributing to YOLOv5 as easy and transparent as possible. Please see our [Contributing Guide](CONTRIBUTING.md) to get started, and fill out the [YOLOv5 Survey](https://ultralytics.com/survey?utm_source=github&utm_medium=social&utm_campaign=Survey) to send us feedback on your experiences. Thank you to all our contributors!
-
-<a href="https://github.com/ultralytics/yolov5/graphs/contributors"><img src="https://opencollective.com/ultralytics/contributors.svg?width=990" /></a>
-
-
-## <div align="center">Contact</div>
-
-For YOLOv5 bugs and feature requests please visit [GitHub Issues](https://github.com/ultralytics/yolov5/issues). For business inquiries or
-professional support requests please visit [https://ultralytics.com/contact](https://ultralytics.com/contact).
-
-<br>
-
-<div align="center">
-    <a href="https://github.com/ultralytics">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-github.png" width="3%"/>
-    </a>
-    <img width="3%" />
-    <a href="https://www.linkedin.com/company/ultralytics">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-linkedin.png" width="3%"/>
-    </a>
-    <img width="3%" />
-    <a href="https://twitter.com/ultralytics">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-twitter.png" width="3%"/>
-    </a>
-    <img width="3%" />
-    <a href="https://youtube.com/ultralytics">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-youtube.png" width="3%"/>
-    </a>
-    <img width="3%" />
-    <a href="https://www.facebook.com/ultralytics">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-facebook.png" width="3%"/>
-    </a>
-    <img width="3%" />
-    <a href="https://www.instagram.com/ultralytics/">
-        <img src="https://github.com/ultralytics/yolov5/releases/download/v1.0/logo-social-instagram.png" width="3%"/>
-    </a>
-</div>

src/Guide_stick_system/image_recognition/export.py

@@ -1,369 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Export a YOLOv5 PyTorch model to TorchScript, ONNX, CoreML, TensorFlow (saved_model, pb, TFLite, TF.js,) formats
-TensorFlow exports authored by https://github.com/zldrobit
-
-Usage:
-    $ python path/to/export.py --weights yolov5s.pt --include torchscript onnx coreml saved_model pb tflite tfjs
-
-Inference:
-    $ python path/to/detect.py --weights yolov5s.pt
-                                         yolov5s.onnx  (must export with --dynamic)
-                                         yolov5s_saved_model
-                                         yolov5s.pb
-                                         yolov5s.tflite
-
-TensorFlow.js: 
-    $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
-    $ npm install
-    $ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model
-    $ npm start
-"""
-
-import argparse
-import json
-import os
-import subprocess
-import sys
-import time
-from pathlib import Path
-
-import torch
-import torch.nn as nn
-from torch.utils.mobile_optimizer import optimize_for_mobile
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[0]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
-
-from models.common import Conv
-from models.experimental import attempt_load
-from models.yolo import Detect
-from utils.activations import SiLU
-from utils.datasets import LoadImages
-from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, colorstr, file_size, print_args,
-                           url2file)
-from utils.torch_utils import select_device
-
-
-def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
-    # YOLOv5 TorchScript model export
-    try:
-        LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...')
-        f = file.with_suffix('.torchscript.pt')
-
-        ts = torch.jit.trace(model, im, strict=False)
-        d = {"shape": im.shape, "stride": int(max(model.stride)), "names": model.names}
-        extra_files = {'config.txt': json.dumps(d)}  # torch._C.ExtraFilesMap()
-        (optimize_for_mobile(ts) if optimize else ts).save(f, _extra_files=extra_files)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-    except Exception as e:
-        LOGGER.info(f'{prefix} export failure: {e}')
-
-
-def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
-    # YOLOv5 ONNX export
-    try:
-        check_requirements(('onnx',))
-        import onnx
-
-        LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
-        f = file.with_suffix('.onnx')
-
-        torch.onnx.export(model, im, f, verbose=False, opset_version=opset,
-                          training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
-                          do_constant_folding=not train,
-                          input_names=['images'],
-                          output_names=['output'],
-                          dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # shape(1,3,640,640)
-                                        'output': {0: 'batch', 1: 'anchors'}  # shape(1,25200,85)
-                                        } if dynamic else None)
-
-        # Checks
-        model_onnx = onnx.load(f)  # load onnx model
-        onnx.checker.check_model(model_onnx)  # check onnx model
-        # LOGGER.info(onnx.helper.printable_graph(model_onnx.graph))  # print
-
-        # Simplify
-        if simplify:
-            try:
-                check_requirements(('onnx-simplifier',))
-                import onnxsim
-
-                LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
-                model_onnx, check = onnxsim.simplify(
-                    model_onnx,
-                    dynamic_input_shape=dynamic,
-                    input_shapes={'images': list(im.shape)} if dynamic else None)
-                assert check, 'assert check failed'
-                onnx.save(model_onnx, f)
-            except Exception as e:
-                LOGGER.info(f'{prefix} simplifier failure: {e}')
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-        LOGGER.info(f"{prefix} run --dynamic ONNX model inference with: 'python detect.py --weights {f}'")
-    except Exception as e:
-        LOGGER.info(f'{prefix} export failure: {e}')
-
-
-def export_coreml(model, im, file, prefix=colorstr('CoreML:')):
-    # YOLOv5 CoreML export
-    ct_model = None
-    try:
-        check_requirements(('coremltools',))
-        import coremltools as ct
-
-        LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
-        f = file.with_suffix('.mlmodel')
-
-        model.train()  # CoreML exports should be placed in model.train() mode
-        ts = torch.jit.trace(model, im, strict=False)  # TorchScript model
-        ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
-        ct_model.save(f)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-    return ct_model
-
-
-def export_saved_model(model, im, file, dynamic,
-                       tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
-                       conf_thres=0.25, prefix=colorstr('TensorFlow saved_model:')):
-    # YOLOv5 TensorFlow saved_model export
-    keras_model = None
-    try:
-        import tensorflow as tf
-        from tensorflow import keras
-
-        from models.tf import TFDetect, TFModel
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
-        f = str(file).replace('.pt', '_saved_model')
-        batch_size, ch, *imgsz = list(im.shape)  # BCHW
-
-        tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
-        im = tf.zeros((batch_size, *imgsz, 3))  # BHWC order for TensorFlow
-        y = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
-        inputs = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
-        outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
-        keras_model = keras.Model(inputs=inputs, outputs=outputs)
-        keras_model.trainable = False
-        keras_model.summary()
-        keras_model.save(f, save_format='tf')
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-    return keras_model
-
-
-def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:')):
-    # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
-    try:
-        import tensorflow as tf
-        from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
-        f = file.with_suffix('.pb')
-
-        m = tf.function(lambda x: keras_model(x))  # full model
-        m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
-        frozen_func = convert_variables_to_constants_v2(m)
-        frozen_func.graph.as_graph_def()
-        tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:')):
-    # YOLOv5 TensorFlow Lite export
-    try:
-        import tensorflow as tf
-
-        from models.tf import representative_dataset_gen
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
-        batch_size, ch, *imgsz = list(im.shape)  # BCHW
-        f = str(file).replace('.pt', '-fp16.tflite')
-
-        converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
-        converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
-        converter.target_spec.supported_types = [tf.float16]
-        converter.optimizations = [tf.lite.Optimize.DEFAULT]
-        if int8:
-            dataset = LoadImages(check_dataset(data)['train'], img_size=imgsz, auto=False)  # representative data
-            converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib)
-            converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
-            converter.target_spec.supported_types = []
-            converter.inference_input_type = tf.uint8  # or tf.int8
-            converter.inference_output_type = tf.uint8  # or tf.int8
-            converter.experimental_new_quantizer = False
-            f = str(file).replace('.pt', '-int8.tflite')
-
-        tflite_model = converter.convert()
-        open(f, "wb").write(tflite_model)
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
-    # YOLOv5 TensorFlow.js export
-    try:
-        check_requirements(('tensorflowjs',))
-        import re
-
-        import tensorflowjs as tfjs
-
-        LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
-        f = str(file).replace('.pt', '_web_model')  # js dir
-        f_pb = file.with_suffix('.pb')  # *.pb path
-        f_json = f + '/model.json'  # *.json path
-
-        cmd = f"tensorflowjs_converter --input_format=tf_frozen_model " \
-              f"--output_node_names='Identity,Identity_1,Identity_2,Identity_3' {f_pb} {f}"
-        subprocess.run(cmd, shell=True)
-
-        json = open(f_json).read()
-        with open(f_json, 'w') as j:  # sort JSON Identity_* in ascending order
-            subst = re.sub(
-                r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
-                r'"Identity.?.?": {"name": "Identity.?.?"}, '
-                r'"Identity.?.?": {"name": "Identity.?.?"}, '
-                r'"Identity.?.?": {"name": "Identity.?.?"}}}',
-                r'{"outputs": {"Identity": {"name": "Identity"}, '
-                r'"Identity_1": {"name": "Identity_1"}, '
-                r'"Identity_2": {"name": "Identity_2"}, '
-                r'"Identity_3": {"name": "Identity_3"}}}',
-                json)
-            j.write(subst)
-
-        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
-    except Exception as e:
-        LOGGER.info(f'\n{prefix} export failure: {e}')
-
-
-@torch.no_grad()
-def run(data=ROOT / 'data/coco128.yaml',  # 'dataset.yaml path'
-        weights=ROOT / 'yolov5s.pt',  # weights path
-        imgsz=(640, 640),  # image (height, width)
-        batch_size=1,  # batch size
-        device='cpu',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
-        include=('torchscript', 'onnx', 'coreml'),  # include formats
-        half=False,  # FP16 half-precision export
-        inplace=False,  # set YOLOv5 Detect() inplace=True
-        train=False,  # model.train() mode
-        optimize=False,  # TorchScript: optimize for mobile
-        int8=False,  # CoreML/TF INT8 quantization
-        dynamic=False,  # ONNX/TF: dynamic axes
-        simplify=False,  # ONNX: simplify model
-        opset=12,  # ONNX: opset version
-        topk_per_class=100,  # TF.js NMS: topk per class to keep
-        topk_all=100,  # TF.js NMS: topk for all classes to keep
-        iou_thres=0.45,  # TF.js NMS: IoU threshold
-        conf_thres=0.25  # TF.js NMS: confidence threshold
-        ):
-    t = time.time()
-    include = [x.lower() for x in include]
-    tf_exports = list(x in include for x in ('saved_model', 'pb', 'tflite', 'tfjs'))  # TensorFlow exports
-    imgsz *= 2 if len(imgsz) == 1 else 1  # expand
-    file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights)
-
-    # Load PyTorch model
-    device = select_device(device)
-    assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
-    model = attempt_load(weights, map_location=device, inplace=True, fuse=True)  # load FP32 model
-    nc, names = model.nc, model.names  # number of classes, class names
-
-    # Input
-    gs = int(max(model.stride))  # grid size (max stride)
-    imgsz = [check_img_size(x, gs) for x in imgsz]  # verify img_size are gs-multiples
-    im = torch.zeros(batch_size, 3, *imgsz).to(device)  # image size(1,3,320,192) BCHW iDetection
-
-    # Update model
-    if half:
-        im, model = im.half(), model.half()  # to FP16
-    model.train() if train else model.eval()  # training mode = no Detect() layer grid construction
-    for k, m in model.named_modules():
-        if isinstance(m, Conv):  # assign export-friendly activations
-            if isinstance(m.act, nn.SiLU):
-                m.act = SiLU()
-        elif isinstance(m, Detect):
-            m.inplace = inplace
-            m.onnx_dynamic = dynamic
-            # m.forward = m.forward_export  # assign forward (optional)
-
-    for _ in range(2):
-        y = model(im)  # dry runs
-    LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} ({file_size(file):.1f} MB)")
-
-    # Exports
-    if 'torchscript' in include:
-        export_torchscript(model, im, file, optimize)
-    if 'onnx' in include:
-        export_onnx(model, im, file, opset, train, dynamic, simplify)
-    if 'coreml' in include:
-        export_coreml(model, im, file)
-
-    # TensorFlow Exports
-    if any(tf_exports):
-        pb, tflite, tfjs = tf_exports[1:]
-        assert not (tflite and tfjs), 'TFLite and TF.js models must be exported separately, please pass only one type.'
-        model = export_saved_model(model, im, file, dynamic, tf_nms=tfjs, agnostic_nms=tfjs,
-                                   topk_per_class=topk_per_class, topk_all=topk_all, conf_thres=conf_thres,
-                                   iou_thres=iou_thres)  # keras model
-        if pb or tfjs:  # pb prerequisite to tfjs
-            export_pb(model, im, file)
-        if tflite:
-            export_tflite(model, im, file, int8=int8, data=data, ncalib=100)
-        if tfjs:
-            export_tfjs(model, im, file)
-
-    # Finish
-    LOGGER.info(f'\nExport complete ({time.time() - t:.2f}s)'
-                f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
-                f'\nVisualize with https://netron.app')
-
-
-def parse_opt():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
-    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
-    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
-    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('--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='TorchScript: optimize for mobile')
-    parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization')
-    parser.add_argument('--dynamic', action='store_true', help='ONNX/TF: dynamic axes')
-    parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model')
-    parser.add_argument('--opset', type=int, default=13, help='ONNX: opset version')
-    parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
-    parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
-    parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
-    parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
-    parser.add_argument('--include', nargs='+',
-                        default=['torchscript', 'onnx'],
-                        help='available formats are (torchscript, onnx, coreml, saved_model, pb, tflite, tfjs)')
-    opt = parser.parse_args()
-    print_args(FILE.stem, opt)
-    return opt
-
-
-def main(opt):
-    run(**vars(opt))
-
-
-if __name__ == "__main__":
-    opt = parse_opt()
-    main(opt)

src/Guide_stick_system/image_recognition/hubconf.py

@@ -1,142 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/
-
-Usage:
-    import torch
-    model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
-""" 
-
-import torch
-
-
-def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    """Creates a specified YOLOv5 model
-
-    Arguments:
-        name (str): name of model, i.e. 'yolov5s'
-        pretrained (bool): load pretrained weights into the model
-        channels (int): number of input channels
-        classes (int): number of model classes
-        autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
-        verbose (bool): print all information to screen
-        device (str, torch.device, None): device to use for model parameters
-
-    Returns:
-        YOLOv5 pytorch model
-    """
-    from pathlib import Path
-
-    from models.experimental import attempt_load
-    from models.yolo import Model
-    from utils.downloads import attempt_download
-    from utils.general import check_requirements, intersect_dicts, set_logging
-    from utils.torch_utils import select_device
-
-    file = Path(__file__).resolve()
-    check_requirements(exclude=('tensorboard', 'thop', 'opencv-python'))
-    set_logging(verbose=verbose)
-
-    save_dir = Path('') if str(name).endswith('.pt') else file.parent
-    path = (save_dir / name).with_suffix('.pt')  # checkpoint path
-    try:
-        device = select_device(('0' if torch.cuda.is_available() else 'cpu') if device is None else device)
-
-        if pretrained and channels == 3 and classes == 80:
-            model = attempt_load(path, map_location=device)  # download/load FP32 model
-        else:
-            cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0]  # model.yaml path
-            model = Model(cfg, channels, classes)  # create model
-            if pretrained:
-                ckpt = torch.load(attempt_download(path), map_location=device)  # load
-                csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
-                csd = intersect_dicts(csd, model.state_dict(), exclude=['anchors'])  # intersect
-                model.load_state_dict(csd, strict=False)  # load
-                if len(ckpt['model'].names) == classes:
-                    model.names = ckpt['model'].names  # set class names attribute
-        if autoshape:
-            model = model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
-        return model.to(device)
-
-    except Exception as e:
-        help_url = 'https://github.com/ultralytics/yolov5/issues/36'
-        s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url
-        raise Exception(s) from e
-
-
-def custom(path='path/to/model.pt', autoshape=True, verbose=True, device=None):
-    # YOLOv5 custom or local model
-    return _create(path, autoshape=autoshape, verbose=verbose, device=device)
-
-
-def yolov5n(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-nano model https://github.com/ultralytics/yolov5
-    return _create('yolov5n', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-small model https://github.com/ultralytics/yolov5
-    return _create('yolov5s', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-medium model https://github.com/ultralytics/yolov5
-    return _create('yolov5m', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-large model https://github.com/ultralytics/yolov5
-    return _create('yolov5l', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
-    return _create('yolov5x', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5n6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-nano-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5n6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-small-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5s6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-medium-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5m6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-large-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5l6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
-    # YOLOv5-xlarge-P6 model https://github.com/ultralytics/yolov5
-    return _create('yolov5x6', pretrained, channels, classes, autoshape, verbose, device)
-
-
-if __name__ == '__main__':
-    model = _create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True, verbose=True)  # pretrained
-    # model = custom(path='path/to/model.pt')  # custom
-
-    # Verify inference
-    from pathlib import Path
-
-    import cv2
-    import numpy as np
-    from PIL import Image
-
-    imgs = ['data/images/zidane.jpg',  # filename
-            Path('data/images/zidane.jpg'),  # Path
-            'https://ultralytics.com/images/zidane.jpg',  # URI
-            cv2.imread('data/images/bus.jpg')[:, :, ::-1],  # OpenCV
-            Image.open('data/images/bus.jpg'),  # PIL
-            np.zeros((320, 640, 3))]  # numpy
-
-    results = model(imgs)  # batched inference
-    results.print()
-    results.save()

src/Guide_stick_system/image_recognition/models/common.py

@@ -1,591 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Common modules
-"""
-
-import json
-import math
-import platform
-import warnings
-from copy import copy
-from pathlib import Path
-
-import cv2
-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 exif_transpose, letterbox
-from utils.general import (LOGGER, check_requirements, check_suffix, colorstr, increment_path, make_divisible,
-                           non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh)
-from utils.plots import Annotator, colors, save_one_box
-from utils.torch_utils import time_sync
-
-
-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
-
-
-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().__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 forward_fuse(self, x):
-        return self.act(self.conv(x))
-
-
-class DWConv(Conv):
-    # Depth-wise convolution class
-    def __init__(self, c1, c2, k=1, s=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
-
-
-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).permute(2, 0, 1)
-        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
-
-
-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().__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().__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.SiLU()
-        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().__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 C3SPP(C3):
-    # C3 module with SPP()
-    def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
-        super().__init__(c1, c2, n, shortcut, g, e)
-        c_ = int(c2 * e)
-        self.m = SPP(c_, c_, k)
-
-
-class C3Ghost(C3):
-    # C3 module with GhostBottleneck()
-    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)  # hidden channels
-        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
-
-
-class SPP(nn.Module):
-    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
-    def __init__(self, c1, c2, k=(5, 9, 13)):
-        super().__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)
-        with warnings.catch_warnings():
-            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
-            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
-
-
-class SPPF(nn.Module):
-    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
-    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
-        super().__init__()
-        c_ = c1 // 2  # hidden channels
-        self.cv1 = Conv(c1, c_, 1, 1)
-        self.cv2 = Conv(c_ * 4, c2, 1, 1)
-        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
-
-    def forward(self, x):
-        x = self.cv1(x)
-        with warnings.catch_warnings():
-            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
-            y1 = self.m(x)
-            y2 = self.m(y1)
-            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 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().__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 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().__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().__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 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):
-        b, c, h, w = x.size()  # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
-        s = self.gain
-        x = x.view(b, 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(b, 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):
-        b, c, h, w = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
-        s = self.gain
-        x = x.view(b, 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(b, 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().__init__()
-        self.d = dimension
-
-    def forward(self, x):
-        return torch.cat(x, self.d)
-
-
-class DetectMultiBackend(nn.Module):
-    # YOLOv5 MultiBackend class for python inference on various backends
-    def __init__(self, weights='yolov5s.pt', device=None, dnn=True):
-        # Usage:
-        #   PyTorch:      weights = *.pt
-        #   TorchScript:            *.torchscript.pt
-        #   CoreML:                 *.mlmodel
-        #   TensorFlow:             *_saved_model
-        #   TensorFlow:             *.pb
-        #   TensorFlow Lite:        *.tflite
-        #   ONNX Runtime:           *.onnx
-        #   OpenCV DNN:             *.onnx with dnn=True
-        super().__init__()
-        w = str(weights[0] if isinstance(weights, list) else weights)
-        suffix, suffixes = Path(w).suffix.lower(), ['.pt', '.onnx', '.tflite', '.pb', '', '.mlmodel']
-        check_suffix(w, suffixes)  # check weights have acceptable suffix
-        pt, onnx, tflite, pb, saved_model, coreml = (suffix == x for x in suffixes)  # backend booleans
-        jit = pt and 'torchscript' in w.lower()
-        stride, names = 64, [f'class{i}' for i in range(1000)]  # assign defaults
-
-        if jit:  # TorchScript
-            LOGGER.info(f'Loading {w} for TorchScript inference...')
-            extra_files = {'config.txt': ''}  # model metadata
-            model = torch.jit.load(w, _extra_files=extra_files)
-            if extra_files['config.txt']:
-                d = json.loads(extra_files['config.txt'])  # extra_files dict
-                stride, names = int(d['stride']), d['names']
-        elif pt:  # PyTorch
-            from models.experimental import attempt_load  # scoped to avoid circular import
-            model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device)
-            stride = int(model.stride.max())  # model stride
-            names = model.module.names if hasattr(model, 'module') else model.names  # get class names
-        elif coreml:  # CoreML *.mlmodel
-            import coremltools as ct
-            model = ct.models.MLModel(w)
-        elif dnn:  # ONNX OpenCV DNN
-            LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
-            check_requirements(('opencv-python>=4.5.4',))
-            net = cv2.dnn.readNetFromONNX(w)
-        elif onnx:  # ONNX Runtime
-            LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
-            check_requirements(('onnx', 'onnxruntime-gpu' if torch.has_cuda else 'onnxruntime'))
-            import onnxruntime
-            session = onnxruntime.InferenceSession(w, None)
-        else:  # TensorFlow model (TFLite, pb, saved_model)
-            import tensorflow as tf
-            if pb:  # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
-                def wrap_frozen_graph(gd, inputs, outputs):
-                    x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), [])  # wrapped
-                    return x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs),
-                                   tf.nest.map_structure(x.graph.as_graph_element, outputs))
-
-                LOGGER.info(f'Loading {w} for TensorFlow *.pb inference...')
-                graph_def = tf.Graph().as_graph_def()
-                graph_def.ParseFromString(open(w, 'rb').read())
-                frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0")
-            elif saved_model:
-                LOGGER.info(f'Loading {w} for TensorFlow saved_model inference...')
-                model = tf.keras.models.load_model(w)
-            elif tflite:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
-                if 'edgetpu' in w.lower():
-                    LOGGER.info(f'Loading {w} for TensorFlow Edge TPU inference...')
-                    import tflite_runtime.interpreter as tfli
-                    delegate = {'Linux': 'libedgetpu.so.1',  # install https://coral.ai/software/#edgetpu-runtime
-                                'Darwin': 'libedgetpu.1.dylib',
-                                'Windows': 'edgetpu.dll'}[platform.system()]
-                    interpreter = tfli.Interpreter(model_path=w, experimental_delegates=[tfli.load_delegate(delegate)])
-                else:
-                    LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
-                    interpreter = tf.lite.Interpreter(model_path=w)  # load TFLite model
-                interpreter.allocate_tensors()  # allocate
-                input_details = interpreter.get_input_details()  # inputs
-                output_details = interpreter.get_output_details()  # outputs
-        self.__dict__.update(locals())  # assign all variables to self
-
-    def forward(self, im, augment=False, visualize=False, val=False):
-        # YOLOv5 MultiBackend inference
-        b, ch, h, w = im.shape  # batch, channel, height, width
-        if self.pt:  # PyTorch
-            y = self.model(im) if self.jit else self.model(im, augment=augment, visualize=visualize)
-            return y if val else y[0]
-        elif self.coreml:  # CoreML *.mlmodel
-            im = im.permute(0, 2, 3, 1).cpu().numpy()  # torch BCHW to numpy BHWC shape(1,320,192,3)
-            im = Image.fromarray((im[0] * 255).astype('uint8'))
-            # im = im.resize((192, 320), Image.ANTIALIAS)
-            y = self.model.predict({'image': im})  # coordinates are xywh normalized
-            box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]])  # xyxy pixels
-            conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float)
-            y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
-        elif self.onnx:  # ONNX
-            im = im.cpu().numpy()  # torch to numpy
-            if self.dnn:  # ONNX OpenCV DNN
-                self.net.setInput(im)
-                y = self.net.forward()
-            else:  # ONNX Runtime
-                y = self.session.run([self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0]
-        else:  # TensorFlow model (TFLite, pb, saved_model)
-            im = im.permute(0, 2, 3, 1).cpu().numpy()  # torch BCHW to numpy BHWC shape(1,320,192,3)
-            if self.pb:
-                y = self.frozen_func(x=self.tf.constant(im)).numpy()
-            elif self.saved_model:
-                y = self.model(im, training=False).numpy()
-            elif self.tflite:
-                input, output = self.input_details[0], self.output_details[0]
-                int8 = input['dtype'] == np.uint8  # is TFLite quantized uint8 model
-                if int8:
-                    scale, zero_point = input['quantization']
-                    im = (im / scale + zero_point).astype(np.uint8)  # de-scale
-                self.interpreter.set_tensor(input['index'], im)
-                self.interpreter.invoke()
-                y = self.interpreter.get_tensor(output['index'])
-                if int8:
-                    scale, zero_point = output['quantization']
-                    y = (y.astype(np.float32) - zero_point) * scale  # re-scale
-            y[..., 0] *= w  # x
-            y[..., 1] *= h  # y
-            y[..., 2] *= w  # w
-            y[..., 3] *= h  # h
-        y = torch.tensor(y)
-        return (y, []) if val else y
-
-
-class AutoShape(nn.Module):
-    # YOLOv5 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, i.e. = [0, 15, 16] for COCO persons, cats and dogs
-    multi_label = False  # NMS multiple labels per box
-    max_det = 1000  # maximum number of detections per image
-
-    def __init__(self, model):
-        super().__init__()
-        self.model = model.eval()
-
-    def autoshape(self):
-        LOGGER.info('AutoShape already enabled, skipping... ')  # model already converted to model.autoshape()
-        return self
-
-    def _apply(self, fn):
-        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
-        self = super()._apply(fn)
-        m = self.model.model[-1]  # Detect()
-        m.stride = fn(m.stride)
-        m.grid = list(map(fn, m.grid))
-        if isinstance(m.anchor_grid, list):
-            m.anchor_grid = list(map(fn, m.anchor_grid))
-        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:
-        #   file:       imgs = 'data/images/zidane.jpg'  # str or PosixPath
-        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
-        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
-        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # 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_sync()]
-        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, Path)):  # filename or uri
-                im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
-                im = np.asarray(exif_transpose(im))
-            elif isinstance(im, Image.Image):  # PIL Image
-                im, f = np.asarray(exif_transpose(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_sync())
-
-        with amp.autocast(enabled=p.device.type != 'cpu'):
-            # Inference
-            y = self.model(x, augment, profile)[0]  # forward
-            t.append(time_sync())
-
-            # Post-process
-            y = non_max_suppression(y, self.conf, iou_thres=self.iou, classes=self.classes,
-                                    multi_label=self.multi_label, max_det=self.max_det)  # NMS
-            for i in range(n):
-                scale_coords(shape1, y[i][:, :4], shape0[i])
-
-            t.append(time_sync())
-            return Detections(imgs, y, files, t, self.names, x.shape)
-
-
-class Detections:
-    # YOLOv5 detections class for inference results
-    def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
-        super().__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('')):
-        crops = []
-        for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
-            s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
-            if pred.shape[0]:
-                for c in pred[:, -1].unique():
-                    n = (pred[:, -1] == c).sum()  # detections per class
-                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
-                if show or save or render or crop:
-                    annotator = Annotator(im, example=str(self.names))
-                    for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
-                        label = f'{self.names[int(cls)]} {conf:.2f}'
-                        if crop:
-                            file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
-                            crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
-                                          'im': save_one_box(box, im, file=file, save=save)})
-                        else:  # all others
-                            annotator.box_label(box, label, color=colors(cls))
-                    im = annotator.im
-            else:
-                s += '(no detections)'
-
-            im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
-            if pprint:
-                LOGGER.info(s.rstrip(', '))
-            if show:
-                im.show(self.files[i])  # show
-            if save:
-                f = self.files[i]
-                im.save(save_dir / f)  # save
-                if i == self.n - 1:
-                    LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
-            if render:
-                self.imgs[i] = np.asarray(im)
-        if crop:
-            if save:
-                LOGGER.info(f'Saved results to {save_dir}\n')
-            return crops
-
-    def print(self):
-        self.display(pprint=True)  # print results
-        LOGGER.info(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/detect/exp'):
-        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True)  # increment save_dir
-        self.display(save=True, save_dir=save_dir)  # save results
-
-    def crop(self, save=True, save_dir='runs/detect/exp'):
-        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
-        return self.display(crop=True, save=save, save_dir=save_dir)  # crop results
-
-    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().__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)

src/Guide_stick_system/image_recognition/models/experimental.py

@@ -1,120 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-Experimental modules
-"""
-import math
-
-import numpy as np
-import torch
-import torch.nn as nn
-
-from models.common import Conv
-from utils.downloads 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().__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().__init__()
-        self.weight = weight  # apply weights boolean
-        self.iter = range(n - 1)  # iter object
-        if weight:
-            self.w = nn.Parameter(-torch.arange(1.0, 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 MixConv2d(nn.Module):
-    # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
-    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):  # ch_in, ch_out, kernel, stride, ch_strategy
-        super().__init__()
-        n = len(k)  # number of convolutions
-        if equal_ch:  # equal c_ per group
-            i = torch.linspace(0, n - 1E-6, c2).floor()  # c2 indices
-            c_ = [(i == g).sum() for g in range(n)]  # intermediate channels
-        else:  # equal weight.numel() per group
-            b = [c2] + [0] * n
-            a = np.eye(n + 1, n, 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_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
-        self.bn = nn.BatchNorm2d(c2)
-        self.act = nn.SiLU()
-
-    def forward(self, x):
-        return 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().__init__()
-
-    def forward(self, x, augment=False, profile=False, visualize=False):
-        y = []
-        for module in self:
-            y.append(module(x, augment, profile, visualize)[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, fuse=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]:
-        ckpt = torch.load(attempt_download(w), map_location=map_location)  # load
-        if fuse:
-            model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval())  # FP32 model
-        else:
-            model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval())  # without layer fuse
-
-    # 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
-            if type(m) is Detect:
-                if not isinstance(m.anchor_grid, list):  # new Detect Layer compatibility
-                    delattr(m, 'anchor_grid')
-                    setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
-        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

src/Guide_stick_system/image_recognition/models/hub/anchors.yaml

@@ -1,59 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-# Default 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

src/Guide_stick_system/image_recognition/models/hub/yolov3-spp.yaml

@@ -1,51 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov3-tiny.yaml

@@ -1,41 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov3.yaml

@@ -1,51 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5-bifpn.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 BiFPN 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, 6], 1, Concat, [1]],  # cat P4 <--- BiFPN change
-   [-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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5-fpn.yaml

@@ -1,42 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 FPN head
-head:
-  [[-1, 3, C3, [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, C3, [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, C3, [256, False]],  # 18 (P3/8-small)
-
-   [[18, 14, 10], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5-p2.yaml

@@ -1,54 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors: 3  # auto-anchor evolves 3 anchors per P output layer
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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)
-
-   [[21, 24, 27, 30], 1, Detect, [nc, anchors]],  # Detect(P2, P3, P4, P5)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5-p6.yaml

@@ -1,56 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors: 3  # auto-anchor 3 anchors per P output layer
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5-p7.yaml

@@ -1,67 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-anchors: 3  # auto-anchor 3 anchors per P output layer
-
-# YOLOv5 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1280]],
-   [-1, 1, SPPF, [1280, 5]],  # 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5-panet.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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, 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5l6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5m6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.67  # model depth multiple
-width_multiple: 0.75  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5n6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.25  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5s-ghost.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
-   [-1, 1, GhostConv, [128, 3, 2]],  # 1-P2/4
-   [-1, 3, C3Ghost, [128]],
-   [-1, 1, GhostConv, [256, 3, 2]],  # 3-P3/8
-   [-1, 6, C3Ghost, [256]],
-   [-1, 1, GhostConv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3Ghost, [512]],
-   [-1, 1, GhostConv, [1024, 3, 2]],  # 7-P5/32
-   [-1, 3, C3Ghost, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 head
-head:
-  [[-1, 1, GhostConv, [512, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
-   [-1, 3, C3Ghost, [512, False]],  # 13
-
-   [-1, 1, GhostConv, [256, 1, 1]],
-   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
-   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
-   [-1, 3, C3Ghost, [256, False]],  # 17 (P3/8-small)
-
-   [-1, 1, GhostConv, [256, 3, 2]],
-   [[-1, 14], 1, Concat, [1]],  # cat head P4
-   [-1, 3, C3Ghost, [512, False]],  # 20 (P4/16-medium)
-
-   [-1, 1, GhostConv, [512, 3, 2]],
-   [[-1, 10], 1, Concat, [1]],  # cat head P5
-   [-1, 3, C3Ghost, [1024, False]],  # 23 (P5/32-large)
-
-   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5s-transformer.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3TR, [1024]],  # 9 <--- C3TR() Transformer module
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5s6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/hub/yolov5x6.yaml

@@ -1,60 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 80  # number of classes
-depth_multiple: 1.33  # model depth multiple
-width_multiple: 1.25  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, SPPF, [1024, 5]],  # 11
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/mask_yolov5l.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 2  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/mask_yolov5m.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 2  # number of classes
-depth_multiple: 0.67  # model depth multiple
-width_multiple: 0.75  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/mask_yolov5s.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 2  # number of classes
-depth_multiple: 0.33  # model depth multiple
-width_multiple: 0.50  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/tf.py

@@ -1,465 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-TensorFlow, Keras and TFLite versions of YOLOv5
-Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
-
-Usage:
-    $ python models/tf.py --weights yolov5s.pt
-
-Export:
-    $ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
-"""
-
-import argparse
-import logging
-import sys
-from copy import deepcopy
-from pathlib import Path
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[1]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-# ROOT = ROOT.relative_to(Path.cwd())  # relative
-
-import numpy as np
-import tensorflow as tf
-import torch
-import torch.nn as nn
-from tensorflow import keras
-
-from models.common import C3, SPP, SPPF, Bottleneck, BottleneckCSP, Concat, Conv, DWConv, Focus, autopad
-from models.experimental import CrossConv, MixConv2d, attempt_load
-from models.yolo import Detect
-from utils.activations import SiLU
-from utils.general import LOGGER, make_divisible, print_args
-
-
-class TFBN(keras.layers.Layer):
-    # TensorFlow BatchNormalization wrapper
-    def __init__(self, w=None):
-        super().__init__()
-        self.bn = keras.layers.BatchNormalization(
-            beta_initializer=keras.initializers.Constant(w.bias.numpy()),
-            gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
-            moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
-            moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
-            epsilon=w.eps)
-
-    def call(self, inputs):
-        return self.bn(inputs)
-
-
-class TFPad(keras.layers.Layer):
-    def __init__(self, pad):
-        super().__init__()
-        self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
-
-    def call(self, inputs):
-        return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
-
-
-class TFConv(keras.layers.Layer):
-    # Standard convolution
-    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
-        # ch_in, ch_out, weights, kernel, stride, padding, groups
-        super().__init__()
-        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
-        assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
-        # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
-        # see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
-
-        conv = keras.layers.Conv2D(
-            c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True,
-            kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
-            bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
-        self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
-        self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
-
-        # YOLOv5 activations
-        if isinstance(w.act, nn.LeakyReLU):
-            self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity
-        elif isinstance(w.act, nn.Hardswish):
-            self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity
-        elif isinstance(w.act, (nn.SiLU, SiLU)):
-            self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity
-        else:
-            raise Exception(f'no matching TensorFlow activation found for {w.act}')
-
-    def call(self, inputs):
-        return self.act(self.bn(self.conv(inputs)))
-
-
-class TFFocus(keras.layers.Layer):
-    # Focus wh information into c-space
-    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
-        # ch_in, ch_out, kernel, stride, padding, groups
-        super().__init__()
-        self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
-
-    def call(self, inputs):  # x(b,w,h,c) -> y(b,w/2,h/2,4c)
-        # inputs = inputs / 255  # normalize 0-255 to 0-1
-        return self.conv(tf.concat([inputs[:, ::2, ::2, :],
-                                    inputs[:, 1::2, ::2, :],
-                                    inputs[:, ::2, 1::2, :],
-                                    inputs[:, 1::2, 1::2, :]], 3))
-
-
-class TFBottleneck(keras.layers.Layer):
-    # Standard bottleneck
-    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None):  # ch_in, ch_out, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
-        self.add = shortcut and c1 == c2
-
-    def call(self, inputs):
-        return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
-
-
-class TFConv2d(keras.layers.Layer):
-    # Substitution for PyTorch nn.Conv2D
-    def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
-        super().__init__()
-        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
-        self.conv = keras.layers.Conv2D(
-            c2, k, s, 'VALID', use_bias=bias,
-            kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
-            bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, )
-
-    def call(self, inputs):
-        return self.conv(inputs)
-
-
-class TFBottleneckCSP(keras.layers.Layer):
-    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
-        # ch_in, ch_out, number, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
-        self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
-        self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
-        self.bn = TFBN(w.bn)
-        self.act = lambda x: keras.activations.relu(x, alpha=0.1)
-        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
-
-    def call(self, inputs):
-        y1 = self.cv3(self.m(self.cv1(inputs)))
-        y2 = self.cv2(inputs)
-        return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
-
-
-class TFC3(keras.layers.Layer):
-    # CSP Bottleneck with 3 convolutions
-    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
-        # ch_in, ch_out, number, shortcut, groups, expansion
-        super().__init__()
-        c_ = int(c2 * e)  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
-        self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
-        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
-
-    def call(self, inputs):
-        return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
-
-
-class TFSPP(keras.layers.Layer):
-    # Spatial pyramid pooling layer used in YOLOv3-SPP
-    def __init__(self, c1, c2, k=(5, 9, 13), w=None):
-        super().__init__()
-        c_ = c1 // 2  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
-        self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
-
-    def call(self, inputs):
-        x = self.cv1(inputs)
-        return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
-
-
-class TFSPPF(keras.layers.Layer):
-    # Spatial pyramid pooling-Fast layer
-    def __init__(self, c1, c2, k=5, w=None):
-        super().__init__()
-        c_ = c1 // 2  # hidden channels
-        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
-        self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
-        self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
-
-    def call(self, inputs):
-        x = self.cv1(inputs)
-        y1 = self.m(x)
-        y2 = self.m(y1)
-        return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
-
-
-class TFDetect(keras.layers.Layer):
-    def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None):  # detection layer
-        super().__init__()
-        self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
-        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 = [tf.zeros(1)] * self.nl  # init grid
-        self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
-        self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]),
-                                      [self.nl, 1, -1, 1, 2])
-        self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
-        self.training = False  # set to False after building model
-        self.imgsz = imgsz
-        for i in range(self.nl):
-            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
-            self.grid[i] = self._make_grid(nx, ny)
-
-    def call(self, inputs):
-        z = []  # inference output
-        x = []
-        for i in range(self.nl):
-            x.append(self.m[i](inputs[i]))
-            # x(bs,20,20,255) to x(bs,3,20,20,85)
-            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
-            x[i] = tf.transpose(tf.reshape(x[i], [-1, ny * nx, self.na, self.no]), [0, 2, 1, 3])
-
-            if not self.training:  # inference
-                y = tf.sigmoid(x[i])
-                xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
-                wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
-                # Normalize xywh to 0-1 to reduce calibration error
-                xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
-                wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
-                y = tf.concat([xy, wh, y[..., 4:]], -1)
-                z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no]))
-
-        return x if self.training else (tf.concat(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()
-        xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
-        return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
-
-
-class TFUpsample(keras.layers.Layer):
-    def __init__(self, size, scale_factor, mode, w=None):  # warning: all arguments needed including 'w'
-        super().__init__()
-        assert scale_factor == 2, "scale_factor must be 2"
-        self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
-        # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
-        # with default arguments: align_corners=False, half_pixel_centers=False
-        # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
-        #                                                            size=(x.shape[1] * 2, x.shape[2] * 2))
-
-    def call(self, inputs):
-        return self.upsample(inputs)
-
-
-class TFConcat(keras.layers.Layer):
-    def __init__(self, dimension=1, w=None):
-        super().__init__()
-        assert dimension == 1, "convert only NCHW to NHWC concat"
-        self.d = 3
-
-    def call(self, inputs):
-        return tf.concat(inputs, self.d)
-
-
-def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
-    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
-    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_str = m
-        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 NameError:
-                pass
-
-        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
-        if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
-            c1, c2 = ch[f], args[0]
-            c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
-
-            args = [c1, c2, *args[1:]]
-            if m in [BottleneckCSP, C3]:
-                args.insert(2, n)
-                n = 1
-        elif m is nn.BatchNorm2d:
-            args = [ch[f]]
-        elif m is Concat:
-            c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
-        elif m is Detect:
-            args.append([ch[x + 1] for x in f])
-            if isinstance(args[1], int):  # number of anchors
-                args[1] = [list(range(args[1] * 2))] * len(f)
-            args.append(imgsz)
-        else:
-            c2 = ch[f]
-
-        tf_m = eval('TF' + m_str.replace('nn.', ''))
-        m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
-            else tf_m(*args, w=model.model[i])  # module
-
-        torch_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 torch_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(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10}  {t:<40}{str(args):<30}')  # print
-        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
-        layers.append(m_)
-        ch.append(c2)
-    return keras.Sequential(layers), sorted(save)
-
-
-class TFModel:
-    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)):  # model, channels, classes
-        super().__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.load(f, Loader=yaml.FullLoader)  # model dict
-
-        # Define model
-        if nc and nc != self.yaml['nc']:
-            LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
-            self.yaml['nc'] = nc  # override yaml value
-        self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
-
-    def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
-                conf_thres=0.25):
-        y = []  # outputs
-        x = inputs
-        for i, m in enumerate(self.model.layers):
-            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
-
-            x = m(x)  # run
-            y.append(x if m.i in self.savelist else None)  # save output
-
-        # Add TensorFlow NMS
-        if tf_nms:
-            boxes = self._xywh2xyxy(x[0][..., :4])
-            probs = x[0][:, :, 4:5]
-            classes = x[0][:, :, 5:]
-            scores = probs * classes
-            if agnostic_nms:
-                nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
-                return nms, x[1]
-            else:
-                boxes = tf.expand_dims(boxes, 2)
-                nms = tf.image.combined_non_max_suppression(
-                    boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False)
-                return nms, x[1]
-
-        return x[0]  # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
-        # x = x[0][0]  # [x(1,6300,85), ...] to x(6300,85)
-        # xywh = x[..., :4]  # x(6300,4) boxes
-        # conf = x[..., 4:5]  # x(6300,1) confidences
-        # cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1))  # x(6300,1)  classes
-        # return tf.concat([conf, cls, xywh], 1)
-
-    @staticmethod
-    def _xywh2xyxy(xywh):
-        # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
-        x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
-        return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
-
-
-class AgnosticNMS(keras.layers.Layer):
-    # TF Agnostic NMS
-    def call(self, input, topk_all, iou_thres, conf_thres):
-        # wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
-        return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input,
-                         fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
-                         name='agnostic_nms')
-
-    @staticmethod
-    def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25):  # agnostic NMS
-        boxes, classes, scores = x
-        class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
-        scores_inp = tf.reduce_max(scores, -1)
-        selected_inds = tf.image.non_max_suppression(
-            boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres)
-        selected_boxes = tf.gather(boxes, selected_inds)
-        padded_boxes = tf.pad(selected_boxes,
-                              paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
-                              mode="CONSTANT", constant_values=0.0)
-        selected_scores = tf.gather(scores_inp, selected_inds)
-        padded_scores = tf.pad(selected_scores,
-                               paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
-                               mode="CONSTANT", constant_values=-1.0)
-        selected_classes = tf.gather(class_inds, selected_inds)
-        padded_classes = tf.pad(selected_classes,
-                                paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
-                                mode="CONSTANT", constant_values=-1.0)
-        valid_detections = tf.shape(selected_inds)[0]
-        return padded_boxes, padded_scores, padded_classes, valid_detections
-
-
-def representative_dataset_gen(dataset, ncalib=100):
-    # Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
-    for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
-        input = np.transpose(img, [1, 2, 0])
-        input = np.expand_dims(input, axis=0).astype(np.float32)
-        input /= 255
-        yield [input]
-        if n >= ncalib:
-            break
-
-
-def run(weights=ROOT / 'yolov5s.pt',  # weights path
-        imgsz=(640, 640),  # inference size h,w
-        batch_size=1,  # batch size
-        dynamic=False,  # dynamic batch size
-        ):
-    # PyTorch model
-    im = torch.zeros((batch_size, 3, *imgsz))  # BCHW image
-    model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
-    y = model(im)  # inference
-    model.info()
-
-    # TensorFlow model
-    im = tf.zeros((batch_size, *imgsz, 3))  # BHWC image
-    tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
-    y = tf_model.predict(im)  # inference
-
-    # Keras model
-    im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
-    keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
-    keras_model.summary()
-
-    LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
-
-
-def parse_opt():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
-    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
-    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
-    parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
-    opt = parser.parse_args()
-    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
-    print_args(FILE.stem, opt)
-    return opt
-
-
-def main(opt):
-    run(**vars(opt))
-
-
-if __name__ == "__main__":
-    opt = parse_opt()
-    main(opt)

src/Guide_stick_system/image_recognition/models/yolo.py

@@ -1,336 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-"""
-YOLO-specific modules
-
-Usage:
-    $ python path/to/models/yolo.py --cfg yolov5s.yaml
-"""
-
-import argparse
-import sys
-from copy import deepcopy
-from pathlib import Path
-
-FILE = Path(__file__).resolve()
-ROOT = FILE.parents[1]  # YOLOv5 root directory
-if str(ROOT) not in sys.path:
-    sys.path.append(str(ROOT))  # add ROOT to PATH
-# ROOT = ROOT.relative_to(Path.cwd())  # relative
-
-from models.common import *
-from models.experimental import *
-from utils.autoanchor import check_anchor_order
-from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
-from utils.plots import feature_visualization
-from utils.torch_utils import (copy_attr, fuse_conv_and_bn, initialize_weights, model_info, scale_img, select_device,
-                               time_sync)
-
-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().__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
-        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
-        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,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):
-        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.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
-                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
-
-                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]  # 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)
-
-    def _make_grid(self, nx=20, ny=20, i=0):
-        d = self.anchors[i].device
-        if check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
-            yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')
-        else:
-            yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
-        grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
-        anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
-            .view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
-        return grid, anchor_grid
-
-
-class Model(nn.Module):
-    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
-        super().__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, encoding='ascii', errors='ignore') 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)
-
-        # 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
-
-        # Init weights, biases
-        initialize_weights(self)
-        self.info()
-        LOGGER.info('')
-
-    def forward(self, x, augment=False, profile=False, visualize=False):
-        if augment:
-            return self._forward_augment(x)  # augmented inference, None
-        return self._forward_once(x, profile, visualize)  # 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)
-        y = self._clip_augmented(y)  # clip augmented tails
-        return torch.cat(y, 1), None  # augmented inference, train
-
-    def _forward_once(self, x, profile=False, visualize=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:
-                self._profile_one_layer(m, x, dt)
-            x = m(x)  # run
-            y.append(x if m.i in self.save else None)  # save output
-            if visualize:
-                feature_visualization(x, m.type, m.i, save_dir=visualize)
-        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 _clip_augmented(self, y):
-        # Clip YOLOv5 augmented inference tails
-        nl = self.model[-1].nl  # number of detection layers (P3-P5)
-        g = sum(4 ** x for x in range(nl))  # grid points
-        e = 1  # exclude layer count
-        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
-        y[0] = y[0][:, :-i]  # large
-        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
-        y[-1] = y[-1][:, i:]  # small
-        return y
-
-    def _profile_one_layer(self, m, x, dt):
-        c = isinstance(m, Detect)  # is final layer, copy input as inplace fix
-        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
-        t = time_sync()
-        for _ in range(10):
-            m(x.copy() if c else x)
-        dt.append((time_sync() - 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}')
-        if c:
-            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")
-
-    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 - 0.999999)) 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 isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
-                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
-                delattr(m, 'bn')  # remove batchnorm
-                m.forward = m.forward_fuse  # update forward
-        self.info()
-        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 _apply(self, fn):
-        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
-        self = super()._apply(fn)
-        m = self.model[-1]  # Detect()
-        if isinstance(m, Detect):
-            m.stride = fn(m.stride)
-            m.grid = list(map(fn, m.grid))
-            if isinstance(m.anchor_grid, list):
-                m.anchor_grid = list(map(fn, m.anchor_grid))
-        return self
-
-
-def parse_model(d, ch):  # model_dict, input_channels(3)
-    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
-    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 NameError:
-                pass
-
-        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
-        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
-                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
-            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, C3Ghost]:
-                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(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # 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')
-    parser.add_argument('--profile', action='store_true', help='profile model speed')
-    parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
-    opt = parser.parse_args()
-    opt.cfg = check_yaml(opt.cfg)  # check YAML
-    print_args(FILE.stem, opt)
-    device = select_device(opt.device)
-
-    # Create model
-    model = Model(opt.cfg).to(device)
-    model.train()
-
-    # Profile
-    if opt.profile:
-        img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
-        y = model(img, profile=True)
-
-    # Test all models
-    if opt.test:
-        for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
-            try:
-                _ = Model(cfg)
-            except Exception as e:
-                print(f'Error in {cfg}: {e}')
-
-    # 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

src/Guide_stick_system/image_recognition/models/yolov5l.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 2  # number of classes
-depth_multiple: 1.0  # model depth multiple
-width_multiple: 1.0  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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)
-  ]

src/Guide_stick_system/image_recognition/models/yolov5m.yaml

@@ -1,48 +0,0 @@
-# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
-
-# Parameters
-nc: 2  # number of classes
-depth_multiple: 0.67  # model depth multiple
-width_multiple: 0.75  # layer channel multiple
-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 v6.0 backbone
-backbone:
-  # [from, number, module, args]
-  [[-1, 1, Conv, [64, 6, 2, 2]],  # 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, 6, 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, 3, C3, [1024]],
-   [-1, 1, SPPF, [1024, 5]],  # 9
-  ]
-
-# YOLOv5 v6.0 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)
-  ]