NanoCode012
|
ccfa9373ae
|
Update to remove "module" attribute check
|
4 years ago |
NanoCode012
|
f83521ab9a
|
Fix save error for multi-gpu
|
4 years ago |
Glenn Jocher
|
ce0c58f678
|
update compute_loss()
|
4 years ago |
Glenn Jocher
|
af41083d52
|
EMA FP16 fix #279
|
4 years ago |
Glenn Jocher
|
f767023c56
|
offset and balance update
|
4 years ago |
Glenn Jocher
|
df224a0d8f
|
EMA bug fix #279
|
4 years ago |
Glenn Jocher
|
f02481c73a
|
Update torch_utils.py
|
4 years ago |
Glenn Jocher
|
fc7c42723d
|
Update utils.py
|
4 years ago |
yxNONG
|
53cdaf6bf5
|
Update utils.py
|
4 years ago |
Glenn Jocher
|
4e62eb90be
|
check_img_size() int() update
|
4 years ago |
Glenn Jocher
|
9a9333d245
|
add replicate() to datasets.py
|
4 years ago |
Glenn Jocher
|
37e13f8846
|
update mosaic border
|
4 years ago |
Glenn Jocher
|
93a6765806
|
update mosaic border
|
4 years ago |
Glenn Jocher
|
77fb8ee082
|
refactor dataloader
|
4 years ago |
Glenn Jocher
|
22fb2b0c25
|
refactor dataloader
|
4 years ago |
Glenn Jocher
|
b8557f87e3
|
add stride to datasets.py
|
4 years ago |
Glenn Jocher
|
3b062254a6
|
update utils.create_pretrained()
|
4 years ago |
Glenn Jocher
|
6c1b87a42e
|
update google_utils import
|
4 years ago |
Glenn Jocher
|
364fcfd7db
|
PANet update
|
4 years ago |
Glenn Jocher
|
fc171e2678
|
check_anchor_order() update
|
4 years ago |
Glenn Jocher
|
1f1917ef56
|
remove fast, add merge
|
4 years ago |
Glenn Jocher
|
024a42f4fd
|
datasets.py vid_formats updated
|
4 years ago |
Glenn Jocher
|
5c2cd711df
|
vid_formats bug fix #146
|
4 years ago |
Glenn Jocher
|
10145833c3
|
strip_optimizer() default to save FP16 model
|
4 years ago |
Glenn Jocher
|
cce95e744d
|
backbone as FP16, save default to FP32
|
4 years ago |
Glenn Jocher
|
9fdb0fbacf
|
AutoAnchor bug fix # 117
|
4 years ago |
Glenn Jocher
|
a557b7d924
|
check_img_size() update
|
4 years ago |
Glenn Jocher
|
034609414e
|
AutoAnchor fitness to screen
|
4 years ago |
Glenn Jocher
|
ef75f7313d
|
AutoAnchor n, imgsz bug fix
|
4 years ago |
Glenn Jocher
|
1dfc28527f
|
AutoAnchor BPR to 4 significant figures
|
4 years ago |
Glenn Jocher
|
4052603e1f
|
AutoAnchor update - improvement check
|
4 years ago |
Glenn Jocher
|
bafbc65ee3
|
AutoAnchor bug fix
|
4 years ago |
Glenn Jocher
|
57a0ae3350
|
AutoAnchor implementation
|
4 years ago |
Glenn Jocher
|
ec81c7b5f2
|
check_anchors() bug fix #90
|
4 years ago |
Glenn Jocher
|
8b26e89006
|
AutoAnchor bug fix #72
|
4 years ago |
Glenn Jocher
|
8fa3724072
|
kmean_anchors() update
|
4 years ago |
Glenn Jocher
|
1c0b6236e3
|
update fast mode
|
4 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.
|
4 years ago |
Glenn Jocher
|
db2c3acd3a
|
updated testing settings, rebalanced towards FP16 latency
|
4 years ago |
Glenn Jocher
|
bd3e389130
|
update google_utils.py
|
4 years ago |
Glenn Jocher
|
c5966abba8
|
glob search bug fix #77
|
4 years ago |
Lornatang
|
54795a4f0a
|
fix problem
|
4 years ago |
Glenn Jocher
|
260b1729f0
|
FP16 inference update
|
4 years ago |
Glenn Jocher
|
335c607a24
|
Update datasets.py
|
4 years ago |
Adam
|
34bf936ce6
|
Add more logging for diagnostics
|
4 years ago |
Glenn Jocher
|
93bbf1b87a
|
best possible recall fix
|
4 years ago |
Glenn Jocher
|
31f3310029
|
assert best possible recall > 0.9 before training
|
4 years ago |
Glenn Jocher
|
099e6f5ebd
|
--img-size stride-multiple verification
|
4 years ago |
Glenn Jocher
|
3a5c5328c5
|
ONNX, BCEBlurWithLogitsLoss, plot_study updates
|
4 years ago |
Trevor Sullivan
|
ac93e9c811
|
Fix Google Drive URI for YOLOv5 weights
|
4 years ago |