Glenn Jocher
|
10145833c3
|
strip_optimizer() default to save FP16 model
|
5 years ago |
|
Glenn Jocher
|
cce95e744d
|
backbone as FP16, save default to FP32
|
5 years ago |
|
Glenn Jocher
|
d9b64c27c2
|
save ckpt in FP16 #119
|
5 years ago |
|
Glenn Jocher
|
9fdb0fbacf
|
AutoAnchor bug fix # 117
|
5 years ago |
|
Glenn Jocher
|
8b6f5826bc
|
update README.md
|
5 years ago |
|
Glenn Jocher
|
2bfd242fa1
|
Merge remote-tracking branch 'origin/master'
|
5 years ago |
|
Glenn Jocher
|
b7ac446d62
|
update README.md
|
5 years ago |
|
Glenn Jocher
|
91de3381e1
|
Merge pull request #112 from imprashr/patch-1
onnx should be 1.6.0
|
5 years ago |
Prashant Rai
|
0071b69994
|
onnx should be 1.6.0
for smoothly export model to onnx, onnx should be 1.6.0
|
5 years ago |
|
Glenn Jocher
|
a557b7d924
|
check_img_size() update
|
5 years ago |
|
Glenn Jocher
|
034609414e
|
AutoAnchor fitness to screen
|
5 years ago |
|
Glenn Jocher
|
ef75f7313d
|
AutoAnchor n, imgsz bug fix
|
5 years ago |
|
Glenn Jocher
|
2daa412575
|
train with multi-gpu half test bug fix #99
|
5 years ago |
|
Glenn Jocher
|
d1e5716610
|
train with multi-gpu half test bug fix #99
|
5 years ago |
|
Glenn Jocher
|
1dfc28527f
|
AutoAnchor BPR to 4 significant figures
|
5 years ago |
|
Glenn Jocher
|
8db51c7002
|
tb_writer bug fix
|
5 years ago |
|
Glenn Jocher
|
4052603e1f
|
AutoAnchor update - improvement check
|
5 years ago |
|
Glenn Jocher
|
afe1df385b
|
dist.destroy_process_group() bug fix
|
5 years ago |
|
Glenn Jocher
|
72d06147b2
|
Multi-GPU disabled in test.py
|
5 years ago |
|
Glenn Jocher
|
bafbc65ee3
|
AutoAnchor bug fix
|
5 years ago |
|
Glenn Jocher
|
57a0ae3350
|
AutoAnchor implementation
|
5 years ago |
|
Glenn Jocher
|
95c46f7245
|
Merge pull request #79 from Lornatang/delete-redundant-thrid-party-library
Delete redundant thrid party library
|
5 years ago |
|
Glenn Jocher
|
5a50491fa1
|
check_anchors bug fix
|
5 years ago |
|
Glenn Jocher
|
05b8ee5ca4
|
check_anchors() bug fix #102
|
5 years ago |
|
Glenn Jocher
|
7c6fd4d670
|
--verbose bug fix #84
|
5 years ago |
|
Glenn Jocher
|
ec81c7b5f2
|
check_anchors() bug fix #90
|
5 years ago |
|
Glenn Jocher
|
e1e3399286
|
ONNX export bug fix #93
|
5 years ago |
|
Glenn Jocher
|
8b26e89006
|
AutoAnchor bug fix #72
|
5 years ago |
|
Glenn Jocher
|
8fa3724072
|
kmean_anchors() update
|
5 years ago |
|
Glenn Jocher
|
bdd9fee841
|
update fast mode
|
5 years ago |
|
Glenn Jocher
|
1c0b6236e3
|
update fast mode
|
5 years ago |
Lornatang
|
8b8b792802
|
There is no need to download extra packages, official bring it with you
I submitted it once in your yolov3 project, you seem to accept it? I'm not sure. I'll submit PR again.
|
5 years ago |
|
Lornatang
|
0c4b4b8817
|
Merge remote-tracking branch 'upstream/master'
|
5 years ago |
|
Lornatang
|
09c1b96136
|
Merge branch 'fix-reference-bugs'
|
5 years ago |
|
Glenn Jocher
|
db2c3acd3a
|
updated testing settings, rebalanced towards FP16 latency
|
5 years ago |
|
Glenn Jocher
|
915b1481fc
|
default check_git_status() to True
|
5 years ago |
|
Glenn Jocher
|
0b514daced
|
FP16 test loss bug fix
|
5 years ago |
|
Glenn Jocher
|
a1748a8d6e
|
test during training default to FP16
|
5 years ago |
|
Glenn Jocher
|
bd3e389130
|
update google_utils.py
|
5 years ago |
|
Glenn Jocher
|
76ca367a01
|
FP16 to FP32 ckpt load
|
5 years ago |
|
Glenn Jocher
|
6fb5ff014c
|
FP16 to FP32 ckpt load
|
5 years ago |
|
Glenn Jocher
|
14523bb030
|
FP16 to FP32 ckpt load
|
5 years ago |
|
Glenn Jocher
|
c5966abba8
|
glob search bug fix #77
|
5 years ago |
|
Glenn Jocher
|
ace56eb5b6
|
Merge pull request #70 from Lornatang/fix-reference-bugs
fix reference problem
|
5 years ago |
Lornatang
|
54795a4f0a
|
fix problem
|
5 years ago |
|
Glenn Jocher
|
45a17ea40c
|
Merge remote-tracking branch 'origin/master'
|
5 years ago |
|
Glenn Jocher
|
e7c24e04ac
|
half() fix #66
|
5 years ago |
|
Glenn Jocher
|
6570336284
|
Merge pull request #65 from Ashing00/master
add "__init__.py" file in <models> folder
|
5 years ago |
ashing
|
62eda5e9c2
|
add "__init__.py" file in <models> folder
|
5 years ago |
|
Glenn Jocher
|
111994956e
|
switch default inference to FP16 on GPU
|
5 years ago |
