yolov5

Commit Graph

Author	SHA1	Message	Date
Glenn Jocher	3004fb5bc1	Automatic m.half() profile on x.half()	3 years ago
Glenn Jocher	0bd9c48609	Update torch_utils.py FLOPS to GFLOPS	3 years ago
Glenn Jocher	394d1c89f3	Input channel yaml['ch'] addition (#1741 )	3 years ago
Glenn Jocher	685d601308	Increase plot_labels() speed (#1736 )	3 years ago
Glenn Jocher	49abc722fc	Update profile_idetection() (#1727 )	3 years ago
Glenn Jocher	d5289b54c4	clean_str() function addition (#1674 ) * clean_str() function addition * cleanup * add euro symbol € * add closing exclamation (spanish) * cleanup	3 years ago
Glenn Jocher	6bd5e8bca7	nn.SiLU() export support (#1713 )	3 years ago
Polydefkis Gkagkos	1fc9d42a64	NMS --classes 0 bug fix (#1710 )	3 years ago
Glenn Jocher	8bc0027afc	Update loss criteria constructor (#1711 )	3 years ago
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>	3 years ago
Glenn Jocher	69ea70cd3b	Add idetection_profile() function to plots.py (#1700 )	3 years ago
Glenn Jocher	54043a9fa4	Streaming --save-txt bug fix (#1672 ) * Streaming --save-txt bug fix * cleanup	3 years ago
Glenn Jocher	ada90e3901	Profile() feature addition (#1673 ) * Profile() feature addition * cleanup	3 years ago
Glenn Jocher	94a7f55c4e	FReLU bias=False bug fix (#1666 )	3 years ago
Glenn Jocher	2e8e02745b	vast.ai compatability updates (#1657 )	3 years ago
Glenn Jocher	fa8f1fb0e9	Simplify autoshape() post-process (#1653 ) * Simplify autoshape() post-process * cleanup * cleanup	3 years ago
Glenn Jocher	84f9bb5d92	Normalized mosaic plotting bug fix (#1647 )	3 years ago
Glenn Jocher	0bb43953eb	Reinstate PR curve sentinel values (#1645 )	3 years ago
Glenn Jocher	68e6ab668b	Hub device mismatch bug fix (#1619 )	3 years ago
Glenn Jocher	791dadb51c	Pycocotools best.pt after COCO train (#1616 ) * Pycocotools best.pt after COCO train * cleanup	3 years ago
Glenn Jocher	8918e63476	Increase FLOPS robustness (#1608 )	3 years ago
Glenn Jocher	f010147578	Update matplotlib.use('Agg') tight (#1583 ) * Update matplotlib tight_layout=True * udpate * udpate * update * png to ps * update * update	3 years ago
Glenn Jocher	784feae30a	Update matplotlib svg backend (#1580 )	3 years ago
Hu Ye	577f298d9b	plot_images() scale bug fix (#1566 ) fix bugs in plot_images	3 years ago
Glenn Jocher	b6ed1104a6	Daemon thread plotting (#1561 ) * Daemon thread plotting * remove process_batch * plot after print	3 years ago
Glenn Jocher	cff9263490	f.read().strip() (#1551 )	3 years ago
Glenn Jocher	9fa7f9f598	f.read().strip()	3 years ago
Glenn Jocher	96a84468b9	Update labels_to_image_weights() (#1545 )	3 years ago
Glenn Jocher	c9798ae0e1	Update plot_study_txt() (#1533 )	3 years ago
Glenn Jocher	0f2057ed33	Targets scaling bug fix (#1529 )	3 years ago
Glenn Jocher	2c3efa430b	Mosaic plots bug fix (#1526 )	3 years ago
Glenn Jocher	12499f1c01	--image_weights bug fix (#1524 )	3 years ago
Glenn Jocher	9728e2b8ae	--image_weights bug fix (#1524 )	3 years ago
Glenn Jocher	e9a0ae6f19	Cache bug fix (#1513 ) * Caching bug fix #1508 * np.zeros((0,5)) x2	3 years ago
yxNONG	b3ceffb513	Add QFocalLoss() (#1482 ) * Update loss.py implement the quality focal loss which is a more general case of focal loss more detail in https://arxiv.org/abs/2006.04388 In the obj loss (or the case cls loss with label smooth), the targets is no long barely be 0 or 1 (can be 0.7), in this case, the normal focal loss is not work accurately quality focal loss in behave the same as focal loss when the target is equal to 0 or 1, and work accurately when targets in (0, 1) example: targets: tensor([[0.6225, 0.0000, 0.0000], [0.9000, 0.0000, 0.0000], [1.0000, 0.0000, 0.0000]]) ___________________________ pred_prob: tensor([[0.6225, 0.2689, 0.1192], [0.7773, 0.5000, 0.2227], [0.8176, 0.8808, 0.1978]]) ____________________________ focal_loss tensor([[0.0937, 0.0328, 0.0039], [0.0166, 0.1838, 0.0199], [0.0039, 1.3186, 0.0145]]) ______________ qfocal_loss tensor([[7.5373e-08, 3.2768e-02, 3.9179e-03], [4.8601e-03, 1.8380e-01, 1.9857e-02], [3.9233e-03, 1.3186e+00, 1.4545e-02]]) we can see that targets[0][0] = 0.6255 is almost the same as pred_prob[0][0] = 0.6225, the targets[1][0] = 0.9 is greater then pred_prob[1][0] = 0.7773 by 0.1227 however, the focal loss[0][0] = 0.0937 larger then focal loss[1][0] = 0.0166 (which against the purpose of focal loss) for the quality focal loss , it implement the case of targets not equal to 0 or 1 * Update loss.py	3 years ago
Glenn Jocher	2026d4c5eb	Update caching (#1496 )	3 years ago
Glenn Jocher	bde5d9aaaa	Update caching (#1496 )	3 years ago
Glenn Jocher	0822cda781	Update caching (#1496 )	3 years ago
Glenn Jocher	89c7a5b8dc	Update caching (#1496 )	3 years ago
igornishka	44f42b1589	changed prints to logging in utils/datasets (#1315 ) Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	3 years ago
Glenn Jocher	7aeef2dca5	Prevent PR plotting (#1489 )	3 years ago
Glenn Jocher	354109c54c	Autosplit (#1488 )	3 years ago
Glenn Jocher	4798e66fdf	Autosplit (#1488 )	3 years ago
Glenn Jocher	0a3ff71ae0	Confusion matrix (#1474 ) * initial commit * add plotting * matrix to cpu * bug fix * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * seaborn pandas to requirements.txt * seaborn pandas to requirements.txt * update wandb plotting * remove pandas * if plots * if plots * if plots * if plots * if plots * initial commit * add plotting * matrix to cpu * bug fix * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * update plot * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * cleanup * seaborn pandas to requirements.txt * seaborn pandas to requirements.txt * update wandb plotting * remove pandas * if plots * if plots * if plots * if plots * if plots * Cat apriori to autolabels * cleanup	3 years ago
Glenn Jocher	95fa65339f	Cat apriori to autolabels (#1484 )	3 years ago
Glenn Jocher	201bafc7cf	Sync train and test iou_thresh (#1465 ) * Sync train and test iou_thresh * Sync train and test iou_thresh * weights names .lower() * Notebook update	3 years ago
Glenn Jocher	a70e554fc3	Remove redundant downloads mirror (#1461 )	3 years ago
Glenn Jocher	394131c2aa	Use torchvision.ops.nms (#1460 )	3 years ago
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>	3 years ago
Glenn Jocher	64bce3c822	Update labels.png with rectangles fix (#1432 )	3 years ago

... 2 3 4 5 6 ...

337 Commits (2d41e70e828c215a3c8486bb24ac2169084079f1)