9f27902368
Improved FLOPS computation ( #1398 )
2020-11-14 14:48:55 +01:00
d8f5fcfe87
Improved FLOPS computation ( #1398 )
...
* Improved FLOPS computation
* update comment
2020-11-14 14:39:46 +01:00
fe341fa44d
Utils reorganization ( #1392 )
...
* Utils reorganization
* Add new utils files
* cleanup
* simplify
* reduce datasets.py
* remove evolve.sh
* loadWebcam cleanup
2020-11-14 11:50:32 +01:00
19e2482458
PyTorch version to screen and cleanup ( #1325 )
...
* Create flatten_recursive() helper function
* cleanup
* print torch version
2020-11-09 12:24:11 +01:00
c8c5ef36c9
PyTorch 1.7.0 Compatibility Updates ( #1233 )
...
* torch 1.7.0 compatibility updates
* add inference verification
2020-10-28 15:03:50 +01:00
3b57cb5641
Simplified inference ( #1153 )
2020-10-15 20:10:08 +02:00
124f0e8212
torchvision nms bug fix
2020-10-06 15:09:24 +02:00
883924d9dc
classifier, export, torch seed updates
2020-10-06 14:54:02 +02:00
89655a84f2
.fuse() gradient introduction bug fix
2020-09-20 11:57:19 -07:00
c5969f79f5
add support for DWConv fuse operation ( #898 )
...
* the value should be a list to unpacking
* filter the None labels
* update readme to remove apex dependency
* add support for DWConv fuse operation
2020-09-01 22:18:42 -07:00
b42e8a531b
optimize imports
2020-08-20 21:17:40 -07:00
26c3b11fdc
Update torch_utils.py ( #751 )
2020-08-16 13:58:59 -07:00
f5da528d28
reformat code
2020-08-14 11:53:44 -07:00
4949401a94
Fix redundant outputs via Logging in DDP training ( #500 )
...
* Change print to logging
* Clean function set_logging
* Add line spacing
* Change leftover prints to log
* Fix scanning labels output
* Fix rank naming
* Change leftover print to logging
* Reorganized DDP variables
* Fix type error
* Make quotes consistent
* Fix spelling
* Clean function call
* Add line spacing
* Update datasets.py
* Update train.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-08-11 11:18:45 -07:00
3c6e2f7668
Single-source training ( #680 )
...
* Single-source training
* Extract hyperparameters into seperate files
* weight decay scientific notation yaml reader bug fix
* remove import glob
* intersect_dicts() implementation
* 'or' bug fix
* .to(device) bug fix
2020-08-09 02:12:44 -07:00
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
2020-07-31 10:52:45 -07:00
1d17b9af0f
update yolo.py TTA flexibility and extensibility ( #506 )
...
* update yolo.py TTA flexibility and extensibility
* Update scale_img()
2020-07-24 11:42:23 -07:00
9da56b62dd
v2.0 Release ( #491 )
...
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-07-23 15:34:23 -07:00
2377e5f6ee
FP16 EMA bug fix
2020-07-13 15:47:46 -07:00
41ff83a98d
update torch_utils.py to FP16 EMA
2020-07-12 12:18:00 -07:00
a586751904
multi-gpu ckpt filesize bug fix #253
2020-07-11 12:35:21 -07:00
24c5a941f0
--resume EMA fix #292
2020-07-09 15:09:06 -07:00
121d90b3f2
update fuse_conv_and_bn()
2020-07-06 11:46:10 -07:00
38f5c1ad1d
pruning and sparsity initial commit
2020-07-05 13:41:21 -07:00
ccfa9373ae
Update to remove "module" attribute check
2020-07-04 23:12:57 +07:00
f83521ab9a
Fix save error for multi-gpu
2020-07-04 16:50:33 +07:00
af41083d52
EMA FP16 fix #279
2020-07-03 16:57:08 -07:00
df224a0d8f
EMA bug fix #279
2020-07-03 11:56:14 -07:00
f02481c73a
Update torch_utils.py
2020-07-02 12:03:45 -07:00
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.
2020-06-16 08:28:52 +08:00
8fe299f179
model fuse
2020-06-07 14:10:30 -07:00
b810b21299
augmented inference
2020-06-05 21:14:15 -07:00
c12023f145
updates
2020-06-05 20:50:43 -07:00
22d6088205
speed-reproducibility fix #17
2020-06-05 13:07:09 -07:00
1e84a23f38
initial commit
2020-05-29 17:04:54 -07:00
Glenn Jocher
tkianai
Francisco Ingham
NanoCode012
Liu Changyu