yolov5

Commit graph

Autor	SHA1	Nachricht	Datum
Glenn Jocher	3004fb5bc1	Automatic m.half() profile on x.half()	vor 3 Jahren
Glenn Jocher	0bd9c48609	Update torch_utils.py FLOPS to GFLOPS	vor 3 Jahren
Glenn Jocher	394d1c89f3	Input channel yaml['ch'] addition (#1741 )	vor 3 Jahren
Glenn Jocher	8bc0027afc	Update loss criteria constructor (#1711 )	vor 3 Jahren
NanoCode012	035ac82ed0	Fix torch multi-GPU --device error (#1701 ) * Fix torch GPU error * Update torch_utils.py single-line device = Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	vor 3 Jahren
Glenn Jocher	ada90e3901	Profile() feature addition (#1673 ) * Profile() feature addition * cleanup	vor 3 Jahren
Glenn Jocher	8918e63476	Increase FLOPS robustness (#1608 )	vor 3 Jahren
yujun	05a955a3f6	FLOPS computation device bug fix (#1447 ) * Update torch_utils.py fix issue#113 , inputs device should be same with model parameters' device * Update torch_utils.py * Update torch_utils.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	vor 3 Jahren
Glenn Jocher	9f27902368	Improved FLOPS computation (#1398 )	vor 3 Jahren
Glenn Jocher	d8f5fcfe87	Improved FLOPS computation (#1398 ) * Improved FLOPS computation * update comment	vor 3 Jahren
Glenn Jocher	fe341fa44d	Utils reorganization (#1392 ) * Utils reorganization * Add new utils files * cleanup * simplify * reduce datasets.py * remove evolve.sh * loadWebcam cleanup	vor 3 Jahren
Glenn Jocher	19e2482458	PyTorch version to screen and cleanup (#1325 ) * Create flatten_recursive() helper function * cleanup * print torch version	vor 3 Jahren
Glenn Jocher	c8c5ef36c9	PyTorch 1.7.0 Compatibility Updates (#1233 ) * torch 1.7.0 compatibility updates * add inference verification	vor 3 Jahren
Glenn Jocher	3b57cb5641	Simplified inference (#1153 )	vor 3 Jahren
Glenn Jocher	124f0e8212	torchvision nms bug fix	vor 4 Jahren
Glenn Jocher	883924d9dc	classifier, export, torch seed updates	vor 4 Jahren
Glenn Jocher	89655a84f2	.fuse() gradient introduction bug fix	vor 4 Jahren
tkianai	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	vor 4 Jahren
Glenn Jocher	b42e8a531b	optimize imports	vor 4 Jahren
Francisco Ingham	26c3b11fdc	Update torch_utils.py (#751 )	vor 4 Jahren
Glenn Jocher	f5da528d28	reformat code	vor 4 Jahren
NanoCode012	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>	vor 4 Jahren
Glenn Jocher	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	vor 4 Jahren
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	vor 4 Jahren
Glenn Jocher	1d17b9af0f	update yolo.py TTA flexibility and extensibility (#506 ) * update yolo.py TTA flexibility and extensibility * Update scale_img()	vor 4 Jahren
Glenn Jocher	9da56b62dd	v2.0 Release (#491 ) Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	vor 4 Jahren
Glenn Jocher	2377e5f6ee	FP16 EMA bug fix	vor 4 Jahren
Glenn Jocher	41ff83a98d	update torch_utils.py to FP16 EMA	vor 4 Jahren
Glenn Jocher	a586751904	multi-gpu ckpt filesize bug fix #253	vor 4 Jahren
Glenn Jocher	24c5a941f0	--resume EMA fix #292	vor 4 Jahren
Glenn Jocher	121d90b3f2	update fuse_conv_and_bn()	vor 4 Jahren
Glenn Jocher	38f5c1ad1d	pruning and sparsity initial commit	vor 4 Jahren
NanoCode012	ccfa9373ae	Update to remove "module" attribute check	vor 4 Jahren
NanoCode012	f83521ab9a	Fix save error for multi-gpu	vor 4 Jahren
Glenn Jocher	af41083d52	EMA FP16 fix #279	vor 4 Jahren
Glenn Jocher	df224a0d8f	EMA bug fix #279	vor 4 Jahren
Glenn Jocher	f02481c73a	Update torch_utils.py	vor 4 Jahren
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.	vor 4 Jahren
Glenn Jocher	8fe299f179	model fuse	vor 4 Jahren
Glenn Jocher	b810b21299	augmented inference	vor 4 Jahren
Glenn Jocher	c12023f145	updates	vor 4 Jahren
Glenn Jocher	22d6088205	speed-reproducibility fix #17	vor 4 Jahren
Glenn Jocher	1e84a23f38	initial commit	vor 4 Jahren

43 Commits (720afe68e960f1ed5c6f65e5cf1833a83024655d)