yolov5

Commit Graph

Author	SHA1	Message	Date
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	4 years ago
Glenn Jocher	d3f9bf2bb7	Update datasets.py	4 years ago
NanoCode012	1e15aad6f9	Add InfiniteDataLoader class (#876 ) * Add InfiniteDataLoader Only initializes at first epoch. Saves time. * Moved class to a better location	4 years ago
Glenn Jocher	987c226849	seaborn plotting correlogram addition	4 years ago
rafale77	9776e70988	torch.ops.torchvision.nms (#860 ) Don't load the entire torchvision library just for nms when the function is already in the torch library.	4 years ago
Glenn Jocher	31d6c389f2	Update general.py plot_evolution()	4 years ago
Willie Maddox	455f7b8f76	Update general.py (#823 ) Fixes #822 `init_seeds` from `torch_utils` import is being overwritten by function `init_seeds` in `general.py`	4 years ago
Glenn Jocher	5a7d79fbe6	Update general.py bbox_iou() with eps improvements (#736 ) eps reduced to 1e-9 for additional precaution.	4 years ago
Glenn Jocher	82ed33a052	generalize webcam detection with opt.source.isnumeric() (yolov3 #1462 )	4 years ago
Glenn Jocher	4d7f222f73	Update export.py with v3.0 Hardswish() support	4 years ago
Glenn Jocher	8666bc507e	Create evolve.sh for infinite hyp evolution	4 years ago
Glenn Jocher	71209a6099	exportable Hardswish() implementation	4 years ago
Glenn Jocher	f7e075fe93	gsutil cp yaml when evolving to GCP bucket	4 years ago
Glenn Jocher	9dbaa1bbbe	Update plot_results()	4 years ago
Glenn Jocher	ea5e97fb9b	FP16 NMS (#814 )	4 years ago
Glenn Jocher	b42e8a531b	optimize imports	4 years ago
Glenn Jocher	5e0b90de8f	CIoU nan bug fix (#736 )	4 years ago
Glenn Jocher	ebafd1ead5	single command --resume (#756 ) * single command --resume * else check files, remove TODO * argparse.Namespace() * tensorboard lr * bug fix in get_latest_run()	4 years ago
Francisco Ingham	26c3b11fdc	Update torch_utils.py (#751 )	4 years ago
Glenn Jocher	f5da528d28	reformat code	4 years ago
Quan Lin	66744a0df1	Update utils/google_utils.py (#733 ) To download weights from v3.0 instead of v2.0	4 years ago
Glenn Jocher	916d4aad9a	v3.0 Release (#725 ) * initial commit * remove yolov3-spp from test.py study * update study --img range * update mAP * cleanup and speed updates * update README plot	4 years ago
Hatovix	56c2c344ff	Fix list paths (#721 ) * Add list paths on check_dataset * missing raise statement * Update general.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Marc	a925f283a7	max workers for dataloader (#722 )	4 years ago
Glenn Jocher	9f482cbcb8	utils.general comment updates/bug fixes	4 years ago
Marc	1f92422e20	Github release assets model autodownload (#711 ) * assets autodownload * Update google_utils.py * Update google_utils.py * Update google_utils.py * Update google_utils.py * Update google_utils.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
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>	4 years ago
tkianai	542833c997	Filter the None labels (#705 ) * the value should be a list to unpacking * filter the None labels	4 years ago
tkianai	9ae868364a	the value should be a list to unpacking (#688 )	4 years ago
Glenn Jocher	41523e2c91	Dataset autodownload feature addition (#685 ) * initial commit * move download scripts into data/scripts * new check_dataset() function in general.py * move check_dataset() out of with context * Update general.py * DDP update * Update general.py	4 years ago
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	4 years ago
Glenn Jocher	3fcd365ba3	Fix curl download on Windows (#669 )	4 years ago
NanoCode012	fe5b3f8712	Fix curl download on Windows (#669 ) * Update ci-testing.yml * Fix windows download * Fix cookie and curl download issue from gdrive * Revert "Update ci-testing.yml" This reverts commit `7389d2238d`. * Update google_utils.py PEP8 * Update google_utils.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	7eaf225d55	zero-target training bug fix (#609 )	4 years ago
Glenn Jocher	f346da9f2b	update activations.py	4 years ago
Jirka Borovec	d5b6416c87	Explicit Imports (#498 ) * expand imports * optimize * miss * fix	4 years ago
Glenn Jocher	ec7a926163	AutoAnchor update to display anchors/target	4 years ago
Glenn Jocher	d989bc9260	remove NBSP	4 years ago
Glenn Jocher	023e37807c	hyperparameter evolution update (#566 )	4 years ago
Glenn Jocher	64e6d199ba	hyperparameter evolution update (#566 )	4 years ago
Glenn Jocher	305c6a028a	compute_loss() leaf variable update	4 years ago
Glenn Jocher	c1a2a7a411	hyperparameter evolution bug fix (#566 )	4 years ago
Glenn Jocher	e32abb5fb9	hyperparameter evolution bug fix (#566 )	4 years ago
Glenn Jocher	127cbeb3f5	hyperparameter expansion to flips, perspective, mixup	4 years ago
Glenn Jocher	23d2bde01f	leaf variable --single-cls training bug fix (#593 )	4 years ago
Glenn Jocher	bcd452c482	replace random_affine() with random_perspective() Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	bb87276d80	update build_targets() (#589 ) Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
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 years ago
Glenn Jocher	c8892672a7	Funnel ReLU (FReLU) @staticmethod bug fix (#556 ) Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	131782a2aa	Funnel ReLU (FReLU) (#556 ) Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago

1 2 3 4

175 Commits (23a7f29e2d073a77d3fdc67efcc56f989e637b1d)