yolov5

Graphique des révisions

Auteur	SHA1	Message	Date
Glenn Jocher	7cef03dddd	Fix torch `long` to `float` tensor on HUB macOS (#8067 )	il y a 2 ans
Glenn Jocher	1993efd59e	Swap `unsafe_chunk()` for `chunk()` (#7362 ) Eliminates all unsafe function in YOLOv5 out of an abundance of caution.	il y a 2 ans
Glenn Jocher	406ee528f0	Loss and IoU speed improvements (#7361 ) * Loss speed improvements * bbox_iou speed improvements * bbox_ioa speed improvements * box_iou speed improvements * box_iou speed improvements	il y a 2 ans
Jirka Borovec	c3d5ac151e	precommit: yapf (#5494 ) * precommit: yapf * align isort * fix # Conflicts: # utils/plots.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update setup.cfg * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update setup.cfg * Update setup.cfg * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update wandb_utils.py * Update augmentations.py * Update setup.cfg * Update yolo.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update val.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * simplify colorstr * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * val run fix * export.py last comma * Update export.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update hubconf.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * PyTorch Hub tuple fix * PyTorch Hub tuple fix2 * PyTorch Hub tuple fix3 * Update setup Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	il y a 2 ans
Glenn Jocher	05aae17333	`torch.split()` 1.7.0 compatibility fix (#7102 ) * Update loss.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update loss.py Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>	il y a 2 ans
Glenn Jocher	a2d617ece9	Update loss for FP16 `tobj` (#7088 )	il y a 2 ans
Glenn Jocher	6f128031d0	Update loss.py with `if self.gr < 1:` (#7087 ) * Update loss.py with `if self.gr < 1:` * Update loss.py	il y a 2 ans
Glenn Jocher	b0ba101ac0	`ComputeLoss()` indexing/speed improvements (#7048 ) * device as class attribute * Update loss.py * Update loss.py * improve zeros * tensor split	il y a 2 ans
imyhxy	4e841b9b16	Reuse `de_parallel()` rather than `is_parallel()` (#6354 )	il y a 2 ans
Glenn Jocher	5866646cc8	Fix float zeros format (#5491 ) * Fix float zeros format * 255 to integer	il y a 2 ans
Jirka Borovec	ed887b5976	Add pre-commit CI actions (#4982 ) * define pre-commit * add CI code * configure * apply pre-commit * fstring * apply MD * pre-commit * Update torch_utils.py * Update print strings * notes * Cleanup code-format.yml * Update setup.cfg * Update .pre-commit-config.yaml Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	il y a 2 ans
Zhiqiang Wang	8e5f9ddbdb	Remove redundant `ComputeLoss` code (#4701 )	il y a 3 ans
Glenn Jocher	24bea5e4b7	Standardize headers and docstrings (#4417 ) * Implement new headers * Reformat 1 * Reformat 2 * Reformat 3 - math * Reformat 4 - yaml	il y a 3 ans
Glenn Jocher	96e36a7c91	New CSV Logger (#4148 ) * New CSV Logger * cleanup * move batch plots into Logger * rename comment * Remove total loss from progress bar * mloss :-1 bug fix * Update plot_results() * Update plot_results() * plot_results bug fix	il y a 3 ans
Glenn Jocher	63dd65e7ed	Update train.py (#4136 ) * Refactor train.py * Update imports * Update imports * Update optimizer * cleanup	il y a 3 ans
Glenn Jocher	5ea771d93d	Move IoU functions to metrics.py (#3820 )	il y a 3 ans
Glenn Jocher	8035b61682	Update objectness IoU sort (#3786 )	il y a 3 ans
Glenn Jocher	157aa2f886	Objectness IoU Sort (#3610 ) Co-authored-by: U-LAPTOP-5N89P8V7\banhu <ban.huang@foxmail.com>	il y a 3 ans
Phat Tran	9c803f2f7e	Add --label-smoothing eps argument to train.py (default 0.0) (#2344 ) * Add label smoothing option * Correct data type * add_log * Remove log * Add log * Update loss.py remove comment (too versbose) Co-authored-by: phattran <phat.tranhoang@cyberlogitec.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>	il y a 3 ans
Glenn Jocher	6f5d6fcdaa	Robust objectness loss balancing (#2256 )	il y a 3 ans
Glenn Jocher	bdd88e1ed7	YOLOv5 Segmentation Dataloader Updates (#2188 ) * Update C3 module * Update C3 module * Update C3 module * Update C3 module * update * update * update * update * update * update * update * update * update * updates * updates * updates * updates * updates * updates * updates * updates * updates * updates * update * update * update * update * updates * updates * updates * updates * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update datasets * update * update * update * update attempt_downlaod() * merge * merge * update * update * update * update * update * update * update * update * update * update * parameterize eps * comments * gs-multiple * update * max_nms implemented * Create one_cycle() function * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * GitHub API rate limit fix * update * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * ComputeLoss * astuple * epochs * update * update * ComputeLoss() * update * update * update * update * update * update * update * update * update * update * update * merge * merge * merge * merge * update * update * update * update * commit=tag == tags[-1] * Update cudnn.benchmark * update * update * update * updates * updates * updates * updates * updates * updates * updates * update * update * update * update * update * mosaic9 * update * update * update * update * update * update * institute cache versioning * only display on existing cache * reverse cache exists booleans	il y a 3 ans
Glenn Jocher	86897e3663	Update train.py test batch_size (#2148 ) * Update train.py * Update loss.py	il y a 3 ans
Glenn Jocher	ca9babb8e6	Add ComputeLoss() class (#1950 )	il y a 3 ans
Glenn Jocher	6ab589583c	Add colorstr() (#1887 ) * Add colorful() * update * newline fix * add git description * --always * update loss scaling * update loss scaling 2 * rename to colorstr()	il y a 3 ans
Glenn Jocher	69be8e738f	YOLOv5 v4.0 Release (#1837 ) * Update C3 module * Update C3 module * Update C3 module * Update C3 module * update * update * update * update * update * update * update * update * update * updates * updates * updates * updates * updates * updates * updates * updates * updates * updates * update * update * update * update * updates * updates * updates * updates * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update * update datasets * update * update * update * update attempt_downlaod() * merge * merge * update * update * update * update * update * update * update * update * update * update * parameterize eps * comments * gs-multiple * update * max_nms implemented * Create one_cycle() function * update * update * update * update * update * update * update * update study.png * update study.png * Update datasets.py	il y a 3 ans
Glenn Jocher	8bc0027afc	Update loss criteria constructor (#1711 )	il y a 3 ans
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	il y a 3 ans
Glenn Jocher	fe341fa44d	Utils reorganization (#1392 ) * Utils reorganization * Add new utils files * cleanup * simplify * reduce datasets.py * remove evolve.sh * loadWebcam cleanup	il y a 3 ans

28 Révisions (2dd3db0050cd228e7a7ca3ff72ab7e3f34ea64d7)