yolov5

Commit-Graf

Upphovsman	SHA1	Meddelande	Datum
Glenn Jocher	e9a0ae6f19	Cache bug fix (#1513 ) * Caching bug fix #1508 * np.zeros((0,5)) x2	3 år sedan
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 år sedan
Glenn Jocher	7d629fde05	Update README.md	3 år sedan
Glenn Jocher	d336b31f20	Update README.md	3 år sedan
Glenn Jocher	2026d4c5eb	Update caching (#1496 )	3 år sedan
Glenn Jocher	bde5d9aaaa	Update caching (#1496 )	3 år sedan
Glenn Jocher	0822cda781	Update caching (#1496 )	3 år sedan
Glenn Jocher	89c7a5b8dc	Update caching (#1496 )	3 år sedan
igornishka	44f42b1589	changed prints to logging in utils/datasets (#1315 ) Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	3 år sedan
Glenn Jocher	7aeef2dca5	Prevent PR plotting (#1489 )	3 år sedan
Glenn Jocher	0ddf12e108	Update tutorial.ipynb	3 år sedan
Glenn Jocher	bcac052eb9	Creado con Colaboratory	3 år sedan
Glenn Jocher	8c0e7092a2	Update README.md	3 år sedan
Glenn Jocher	354109c54c	Autosplit (#1488 )	3 år sedan
Glenn Jocher	4798e66fdf	Autosplit (#1488 )	3 år sedan
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 år sedan
Glenn Jocher	95fa65339f	Cat apriori to autolabels (#1484 )	3 år sedan
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 år sedan
Glenn Jocher	d81bc47823	Creado con Colaboratory	3 år sedan
Glenn Jocher	a70e554fc3	Remove redundant downloads mirror (#1461 )	3 år sedan
Glenn Jocher	46c43b7b17	Creado con Colaboratory	3 år sedan
Glenn Jocher	394131c2aa	Use torchvision.ops.nms (#1460 )	3 år sedan
Glenn Jocher	199c9c7874	Detection() device bug fix (#1455 )	3 år sedan
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 år sedan
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	3 år sedan
Glenn Jocher	225845e781	Update test.py for IoU in native image-space (#1439 ) * Update test.py for IoU in native image-space * remove redundant * gn to device * remove output scale_coords * --img-size correction * update * native-space labels * pred to predn * remove clip_coords()	3 år sedan
Glenn Jocher	df0e408962	Merge remote-tracking branch 'origin/master'	3 år sedan
Glenn Jocher	64bce3c822	Update labels.png with rectangles fix (#1432 )	3 år sedan
Glenn Jocher	bd29a1c946	PosixPath to str webcam bug fix (#1437 )	3 år sedan
Glenn Jocher	1542ccadb2	Update labels.png with rectangles (#1432 )	3 år sedan
asim266	9ef4760b74	Rename precision_recall_curve.png bug fix (#1431 ) * fix error in train.py line 400, changed precision-recall_curve.png to precision_recall_curve.png and fix error in test.py of {wandb.init() before wandb.log()} by importing wand and initializing it before wand.log() * Update test.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	3 år sedan
Glenn Jocher	412b113ac6	W&B logging bug fix (#1399 )	3 år sedan
Glenn Jocher	4250f84dfb	Update PR curve (#1428 ) * Update PR curve * legend outside * list(Path().glob())	3 år sedan
Jacobsolawetz	8d2d6d2349	Update img2label_paths() (#1414 )	3 år sedan
Glenn Jocher	97c6a59dd1	PANet anchor order correction (#1420 )	3 år sedan
Glenn Jocher	311de00855	PyTorch Hub and autoShape update (#1415 )	3 år sedan
Glenn Jocher	2aaaec3cca	PyTorch Hub and autoShape update (#1415 )	3 år sedan
Glenn Jocher	7816c0c2d3	PyTorch Hub and autoShape update (#1415 )	3 år sedan
Glenn Jocher	93fc607f07	PyTorch Hub and autoShape update (#1415 )	3 år sedan
Glenn Jocher	f5429260ca	PyTorch Hub and autoShape update (#1415 ) * PyTorch Hub and autoShape update * comment x for imgs * reduce comment	3 år sedan
Glenn Jocher	92c9b72832	Matplotlib AGG backend (#1413 )	3 år sedan
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 / '*' / '.*')	3 år sedan
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	3 år sedan
Glenn Jocher	b7007d03b4	Creado con Colaboratory	3 år sedan
Glenn Jocher	9f27902368	Improved FLOPS computation (#1398 )	3 år sedan
Glenn Jocher	d8f5fcfe87	Improved FLOPS computation (#1398 ) * Improved FLOPS computation * update comment	3 år sedan
Glenn Jocher	0c26c4e831	Increase pycocotools robustness (#1396 )	3 år sedan
Glenn Jocher	9b0f6e33ee	Increase pycocotools robustness (#1396 )	3 år sedan
Glenn Jocher	cf581305db	Creado con Colaboratory	3 år sedan
Glenn Jocher	fe341fa44d	Utils reorganization (#1392 ) * Utils reorganization * Add new utils files * cleanup * simplify * reduce datasets.py * remove evolve.sh * loadWebcam cleanup	3 år sedan

1 2 3 4 5 ...

761 Incheckningar (e9a0ae6f1958881ed3ea0869a3d02cb0da344088) Alla brancher Sök

761 Incheckningar (e9a0ae6f1958881ed3ea0869a3d02cb0da344088)

Alla brancher