yolov5

Commit Graph

Author	SHA1	Message	Date
Glenn Jocher	b6ed1104a6	Daemon thread plotting (#1561 ) * Daemon thread plotting * remove process_batch * plot after print	4 years ago
Glenn Jocher	cff9263490	f.read().strip() (#1551 )	4 years ago
Glenn Jocher	9fa7f9f598	f.read().strip()	4 years ago
Glenn Jocher	96a84468b9	Update labels_to_image_weights() (#1545 )	4 years ago
Glenn Jocher	c9798ae0e1	Update plot_study_txt() (#1533 )	4 years ago
Glenn Jocher	0f2057ed33	Targets scaling bug fix (#1529 )	4 years ago
Glenn Jocher	2c3efa430b	Mosaic plots bug fix (#1526 )	4 years ago
Glenn Jocher	12499f1c01	--image_weights bug fix (#1524 )	4 years ago
Glenn Jocher	9728e2b8ae	--image_weights bug fix (#1524 )	4 years ago
Glenn Jocher	e9a0ae6f19	Cache bug fix (#1513 ) * Caching bug fix #1508 * np.zeros((0,5)) x2	4 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	4 years ago
Glenn Jocher	2026d4c5eb	Update caching (#1496 )	4 years ago
Glenn Jocher	bde5d9aaaa	Update caching (#1496 )	4 years ago
Glenn Jocher	0822cda781	Update caching (#1496 )	4 years ago
Glenn Jocher	89c7a5b8dc	Update caching (#1496 )	4 years ago
igornishka	44f42b1589	changed prints to logging in utils/datasets (#1315 ) Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	4 years ago
Glenn Jocher	7aeef2dca5	Prevent PR plotting (#1489 )	4 years ago
Glenn Jocher	354109c54c	Autosplit (#1488 )	4 years ago
Glenn Jocher	4798e66fdf	Autosplit (#1488 )	4 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	4 years ago
Glenn Jocher	95fa65339f	Cat apriori to autolabels (#1484 )	4 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	4 years ago
Glenn Jocher	a70e554fc3	Remove redundant downloads mirror (#1461 )	4 years ago
Glenn Jocher	394131c2aa	Use torchvision.ops.nms (#1460 )	4 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>	4 years ago
Glenn Jocher	64bce3c822	Update labels.png with rectangles fix (#1432 )	4 years ago
Glenn Jocher	1542ccadb2	Update labels.png with rectangles (#1432 )	4 years ago
Glenn Jocher	4250f84dfb	Update PR curve (#1428 ) * Update PR curve * legend outside * list(Path().glob())	4 years ago
Jacobsolawetz	8d2d6d2349	Update img2label_paths() (#1414 )	4 years ago
Glenn Jocher	f5429260ca	PyTorch Hub and autoShape update (#1415 ) * PyTorch Hub and autoShape update * comment x for imgs * reduce comment	4 years ago
Glenn Jocher	92c9b72832	Matplotlib AGG backend (#1413 )	4 years ago
Glenn Jocher	548a98a391	Recursive directories dataset capability (#1408 ) * Recursive directories dataset capability * x.split('.')[-1] * f += glob.glob(f"{p}{os.sep}*.", recursive=True) * f += glob.glob(str(p / '*.'), recursive=True) * remove . from image and vid formats * .txt to txt * str(p / '*' / '.*')	4 years ago
Glenn Jocher	9c91aeae10	W&B logging add hyperparameters (#1399 ) * W&B logging add hyperparameters * hyp bug fix and image logging updates * if plots and wandb: * cleanup * wandb/ gitignore add * cleanup 2 * cleanup 3 * move wandb import to top of file * wandb evolve * update import * wandb.run.finish() * default anchors: 3	4 years ago
Glenn Jocher	9f27902368	Improved FLOPS computation (#1398 )	4 years ago
Glenn Jocher	d8f5fcfe87	Improved FLOPS computation (#1398 ) * Improved FLOPS computation * update comment	4 years ago
Glenn Jocher	fe341fa44d	Utils reorganization (#1392 ) * Utils reorganization * Add new utils files * cleanup * simplify * reduce datasets.py * remove evolve.sh * loadWebcam cleanup	4 years ago
Glenn Jocher	c4addd7761	Unified '/project/name' results saving (#1377 ) * Project/name update * Update ci-testing.yml * address project with path separator failure mode * Project/name update * address project with path separator failure mode * Update ci-testing.yml * detect.py default --name bug fix * missing rstrip PR * train/exp0 to train/exp	4 years ago
Glenn Jocher	67bf9a974e	Replace 'ground truth' with 'labels' (#1337 ) * Replace 'ground truth' with 'labels' * Using torch... update	4 years ago
Glenn Jocher	19e2482458	PyTorch version to screen and cleanup (#1325 ) * Create flatten_recursive() helper function * cleanup * print torch version	4 years ago
Glenn Jocher	4821d076e2	Increment train, test, detect runs/ (#1322 ) * Increment train, test, detect runs/ * Update ci-testing.yml * inference/images to data/images * move images * runs/exp to runs/train/exp * update 'results saved to %s' str	4 years ago
Glenn Jocher	d3e7778151	imap bug fix	4 years ago
Glenn Jocher	194f16844e	Multi-threaded image caching	4 years ago
Glenn Jocher	ea7e78cb11	Grid indices overflow bug fix (#1316 )	4 years ago
Glenn Jocher	fed5d9cdfb	Grid indices overflow bug fix (#1313 )	4 years ago
Glenn Jocher	2062765e06	auto-download v3.1 models (#1259 )	4 years ago
Glenn Jocher	c8c5ef36c9	PyTorch 1.7.0 Compatibility Updates (#1233 ) * torch 1.7.0 compatibility updates * add inference verification	4 years ago
Glenn Jocher	453acdec67	Update tensorboard logging	4 years ago
Glenn Jocher	8e9b3d0205	Precision-Recall Curve feature update #1206	4 years ago
Glenn Jocher	ed85038c38	Precision-Recall Curve feature update (#1206 ) * Precision-Recall Curve feature update * sentinel value update	4 years ago
Glenn Jocher	481d46cffb	Improved corruption handling during scan and cache (#999 )	4 years ago

... 5 6 7 8 9

427 Commits (d986145b9a57b3c055e8cdea6b40cb979ebfe2e7)