Liu Changyu
c020875b17
PyTorch 1.6.0 update with native AMP ( #573 )
* PyTorch have Automatic Mixed Precision (AMP) Training.
* Fixed the problem of inconsistent code length indentation
* Fixed the problem of inconsistent code length indentation
* Mixed precision training is turned on by default
4 lat temu
Glenn Jocher
1d17b9af0f
update yolo.py TTA flexibility and extensibility ( #506 )
* update yolo.py TTA flexibility and extensibility
* Update scale_img()
4 lat temu
Glenn Jocher
9da56b62dd
v2.0 Release ( #491 )
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
4 lat temu
Glenn Jocher
2377e5f6ee
FP16 EMA bug fix
4 lat temu
Glenn Jocher
41ff83a98d
update torch_utils.py to FP16 EMA
4 lat temu
Glenn Jocher
a586751904
multi-gpu ckpt filesize bug fix #253
4 lat temu
Glenn Jocher
24c5a941f0
--resume EMA fix #292
4 lat temu
Glenn Jocher
121d90b3f2
update fuse_conv_and_bn()
4 lat temu
Glenn Jocher
38f5c1ad1d
pruning and sparsity initial commit
4 lat temu
NanoCode012
ccfa9373ae
Update to remove "module" attribute check
4 lat temu
NanoCode012
f83521ab9a
Fix save error for multi-gpu
4 lat temu
Glenn Jocher
af41083d52
EMA FP16 fix #279
4 lat temu
Glenn Jocher
df224a0d8f
EMA bug fix #279
4 lat temu
Glenn Jocher
f02481c73a
Update torch_utils.py
4 lat temu
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 lat temu
Glenn Jocher
8fe299f179
model fuse
4 lat temu
Glenn Jocher
b810b21299
augmented inference
4 lat temu
Glenn Jocher
c12023f145
updates
4 lat temu
Glenn Jocher
22d6088205
speed-reproducibility fix #17
4 lat temu
Glenn Jocher
1e84a23f38
initial commit
4 lat temu