yolov5

Revīziju grafs

Autors	SHA1	Ziņojums	Datums
Glenn Jocher	86f4247515	Hybrid auto-labelling support (#1646 )	pirms 3 gadiem
Glenn Jocher	0bb43953eb	Reinstate PR curve sentinel values (#1645 )	pirms 3 gadiem
Glenn Jocher	b53c8ac179	Create codeql-analysis.yml (#1644 ) * Create codeql-analysis.yml * Update ci-testing.yml	pirms 3 gadiem
Glenn Jocher	68e6ab668b	Hub device mismatch bug fix (#1619 )	pirms 3 gadiem
Glenn Jocher	791dadb51c	Pycocotools best.pt after COCO train (#1616 ) * Pycocotools best.pt after COCO train * cleanup	pirms 3 gadiem
Glenn Jocher	d929bb656c	Implement default class names (#1609 )	pirms 3 gadiem
Glenn Jocher	efa7a915d8	Update download_weights.sh with usage example (#1613 )	pirms 3 gadiem
Glenn Jocher	8918e63476	Increase FLOPS robustness (#1608 )	pirms 3 gadiem
Glenn Jocher	ba48f867ea	Add bias to Classify() (#1601 )	pirms 3 gadiem
Glenn Jocher	f010147578	Update matplotlib.use('Agg') tight (#1583 ) * Update matplotlib tight_layout=True * udpate * udpate * update * png to ps * update * update	pirms 3 gadiem
Glenn Jocher	784feae30a	Update matplotlib svg backend (#1580 )	pirms 3 gadiem
SergioSanchezMontesUAM	2c99560a98	Update .gitignore datasets dir (#1577 )	pirms 3 gadiem
Hu Ye	577f298d9b	plot_images() scale bug fix (#1566 ) fix bugs in plot_images	pirms 3 gadiem
Glenn Jocher	b6ed1104a6	Daemon thread plotting (#1561 ) * Daemon thread plotting * remove process_batch * plot after print	pirms 3 gadiem
Glenn Jocher	68211f72c9	FROM nvcr.io/nvidia/pytorch:20.10-py3 (#1553 ) * FROM pytorch/pytorch:latest * FROM nvcr.io/nvidia/pytorch:20.10-py3	pirms 3 gadiem
Glenn Jocher	cff9263490	f.read().strip() (#1551 )	pirms 3 gadiem
Glenn Jocher	9fa7f9f598	f.read().strip()	pirms 3 gadiem
Glenn Jocher	96a84468b9	Update labels_to_image_weights() (#1545 )	pirms 3 gadiem
Glenn Jocher	97a5227a1a	Ignore W&B logging dir wandb/ (#1534 )	pirms 3 gadiem
Glenn Jocher	5dbf0c96f4	FROM nvcr.io/nvidia/pytorch:20.11-py3	pirms 3 gadiem
Glenn Jocher	c9798ae0e1	Update plot_study_txt() (#1533 )	pirms 3 gadiem
Glenn Jocher	0f2057ed33	Targets scaling bug fix (#1529 )	pirms 3 gadiem
Glenn Jocher	2c3efa430b	Mosaic plots bug fix (#1526 )	pirms 3 gadiem
Glenn Jocher	12499f1c01	--image_weights bug fix (#1524 )	pirms 3 gadiem
Glenn Jocher	9728e2b8ae	--image_weights bug fix (#1524 )	pirms 3 gadiem
Glenn Jocher	e9a0ae6f19	Cache bug fix (#1513 ) * Caching bug fix #1508 * np.zeros((0,5)) x2	pirms 3 gadiem
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	pirms 3 gadiem
Glenn Jocher	7d629fde05	Update README.md	pirms 3 gadiem
Glenn Jocher	d336b31f20	Update README.md	pirms 3 gadiem
Glenn Jocher	2026d4c5eb	Update caching (#1496 )	pirms 3 gadiem
Glenn Jocher	bde5d9aaaa	Update caching (#1496 )	pirms 3 gadiem
Glenn Jocher	0822cda781	Update caching (#1496 )	pirms 3 gadiem
Glenn Jocher	89c7a5b8dc	Update caching (#1496 )	pirms 3 gadiem
igornishka	44f42b1589	changed prints to logging in utils/datasets (#1315 ) Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	pirms 3 gadiem
Glenn Jocher	7aeef2dca5	Prevent PR plotting (#1489 )	pirms 3 gadiem
Glenn Jocher	0ddf12e108	Update tutorial.ipynb	pirms 3 gadiem
Glenn Jocher	bcac052eb9	Creado con Colaboratory	pirms 3 gadiem
Glenn Jocher	8c0e7092a2	Update README.md	pirms 3 gadiem
Glenn Jocher	354109c54c	Autosplit (#1488 )	pirms 3 gadiem
Glenn Jocher	4798e66fdf	Autosplit (#1488 )	pirms 3 gadiem
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	pirms 3 gadiem
Glenn Jocher	95fa65339f	Cat apriori to autolabels (#1484 )	pirms 3 gadiem
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	pirms 3 gadiem
Glenn Jocher	d81bc47823	Creado con Colaboratory	pirms 3 gadiem
Glenn Jocher	a70e554fc3	Remove redundant downloads mirror (#1461 )	pirms 3 gadiem
Glenn Jocher	46c43b7b17	Creado con Colaboratory	pirms 3 gadiem
Glenn Jocher	394131c2aa	Use torchvision.ops.nms (#1460 )	pirms 3 gadiem
Glenn Jocher	199c9c7874	Detection() device bug fix (#1455 )	pirms 3 gadiem
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>	pirms 3 gadiem
Glenn Jocher	af8aee76b3	Update greetings.yml (#1442 ) * Update greetings.yml * Update --feature-request.md * Update --bug-report.md * Rename --bug-report.md to bug-report.md * Rename -question.md to question.md * Rename --feature-request.md to feature-request.md * Update greetings.yml * Update greetings.yml	pirms 3 gadiem

1 2 3 4 5 ...

786 Revīzijas (86f4247515dfb4cccd413c236ff26b31d8e066b4) Visi atzari Meklēt

786 Revīzijas (86f4247515dfb4cccd413c236ff26b31d8e066b4)

Visi atzari