mirrors
/
yolov5
mirror of https://github.com/ultralytics/yolov5.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
2,221 Commits
10 Branches
10 Tags
584 MiB
Commit Graph

2221 Commits (e83b422a69bbd69628687b2dc50102c08877505c)
 

Author SHA1 Message Date
Glenn Jocher e83b422a69
Update dataset `names` from array to dictionary (#9000) 
* Migrate dataset names to dictionary

* fix check

* backwards compat

* predict fix

* val fix

* Keep dataset stats behavior identical

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-17 17:52:53 +02:00
KieraMengru0907 e8f24d5748
Update README_cn.md (#9001) 
Includes v6.2 updates

Signed-off-by: KieraMengru0907 <108015280+KieraMengru0907@users.noreply.github.com>

Signed-off-by: KieraMengru0907 <108015280+KieraMengru0907@users.noreply.github.com>
 2022-08-17 17:50:32 +02:00
Glenn Jocher fe809b8dad Created using Colaboratory 2022-08-17 16:18:06 +02:00
Glenn Jocher 7c9486e16f
Update `attempt_download(release='v6.2')` (#8998) 
* Update attempt_download(release='v6.2')

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Update README.md

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-17 15:48:17 +02:00
Glenn Jocher e617569107
Improve classification comments (#8997) 2022-08-17 15:33:37 +02:00
Glenn Jocher d3ea0df8b9
New YOLOv5 Classification Models (#8956) 
* Update

* Logger step fix: Increment step with epochs (#8654)

* enhance

* revert

* allow training from scratch

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update --img argument from train.py 

single line

* fix image size from 640 to 128

* suport custom dataloader and augmentation

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* format

* Update dataloaders.py

* Single line return, single line comment, remove unused argument

* address PR comments

* fix spelling

* don't augment eval set

* use fstring

* update augmentations.py

* new maning convention for transforms

* reverse if statement, inline ops

* reverse if statement, inline ops

* updates

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update dataloaders

* Remove additional if statement

* Remove is_train as redundant

* Cleanup

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup2

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update classifier.py

* Update augmentations.py

* fix: imshow clip warning

* update

* Revert ToTensorV2 removal

* Update classifier.py

* Update normalize values, revert uint8

* normalize image using cv2

* remove dedundant comment

* Update classifier.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* replace print with logger

* commit steps

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

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>

* 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

* Allow logging models from GenericLogger (#8676)

* enhance

* revert

* allow training from scratch

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update --img argument from train.py 

single line

* fix image size from 640 to 128

* suport custom dataloader and augmentation

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* format

* Update dataloaders.py

* Single line return, single line comment, remove unused argument

* address PR comments

* fix spelling

* don't augment eval set

* use fstring

* update augmentations.py

* new maning convention for transforms

* reverse if statement, inline ops

* reverse if statement, inline ops

* updates

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update dataloaders

* Remove additional if statement

* Remove is_train as redundant

* Cleanup

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup2

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update classifier.py

* Update augmentations.py

* fix: imshow clip warning

* update

* Revert ToTensorV2 removal

* Update classifier.py

* Update normalize values, revert uint8

* normalize image using cv2

* remove dedundant comment

* Update classifier.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* replace print with logger

* commit steps

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* support final model logging

* update

* update

* update

* update

* remove curses

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update classifier.py

* Update __init__.py

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>

* Update

* Update

* Update

* Update

* Update dataset download

* Update dataset download

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Pass imgsz to classify_transforms()

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Cos scheduler

* Cos scheduler

* Remove unused args

* Update

* Add seed

* Add seed

* Update

* Update

* Add run(), main()

* Merge master

* Merge master

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Create YOLOv5 BaseModel class (#8829)

* Create BaseModel

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix

* Hub load device fix

* Update

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

* Add experiment

* Merge master

* Attach names

* weight decay = 1e-4

* weight decay = 5e-5

* update smart_optimizer console printout

* fashion-mnist fix

* Merge master

* Update Table

* Update Table

* Remove destroy process group

* add kwargs to forward()

* fuse fix for resnet50

* nc, names fix for resnet50

* nc, names fix for resnet50

* ONNX CPU inference fix

* revert

* cuda

* if augment or visualize

* if augment or visualize

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* New smart_inference_mode()

* Update README

* Refactor into /classify dir

* [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

* reset defaults

* reset defaults

* fix gpu predict

* warmup

* ema half fix

* spacing

* remove data

* remove cache

* remove denormalize

* save run settings

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* verbose false on initial plots

* new save_yaml() function

* Update ci-testing.yml

* Path(data) CI fix

* Separate classification CI

* fix val

* fix val

* fix val

* smartCrossEntropyLoss

* skip validation on hub load

* autodownload with working dir root

* str(data)

* Dataset usage example

* im_show normalize

* im_show normalize

* add imagenet simple names to multibackend

* Add validation speeds

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* 24-space names

* Update bash scripts

* Update permissions

* Add bash script arguments

* remove verbose

* TRT data fix

* names generator fix

* optimize if names

* update usage

* Add local loading

* Verbose=False

* update names printing

* Add Usage examples

* Add Usage examples

* Add Usage examples

* Add Usage examples

* named_children

* reshape_classifier_outputs

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update

* update

* fix CI

* fix incorrect class substitution

* fix incorrect class substitution

* remove denormalize

* ravel fix

* cleanup

* update opt file printing

* update opt file printing

* update defaults

* add opt to checkpoint

* Add warning

* Add comment

* plot half bug fix

* Use NotImplementedError

* fix export shape report

* Fix TRT load

* cleanup CI

* profile comment

* CI fix

* Add cls models

* avoid inplace error

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix usage examples

* Update README

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

* Update README

Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-17 11:59:01 +02:00
Victor Sonck 3456fe65c6
Fix torchvision dependency for ClearML logging (#8993) 
* Replace torchvision annotator with native local Annotator

* Add colored bounding boxes and rewrite for efficiency

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix pep8 issue

* Update clearml_utils.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update clearml_utils.py

* Reduced conf_threshold to 0.25 to match defaults

The 0.25 default conf threshold value is used a default throughout YOLOv5 (i.e. in detect.py) and also in other tools like CoreML

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>
 2022-08-17 11:51:07 +02:00
Yana fd004f5648
Fix bug with resume (#8912) 
* Fix bug with resume

* restore del on resume=false

* Update train.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-17 00:58:30 +02:00
Glenn Jocher d1dfcab604 Created using Colaboratory 2022-08-16 22:22:52 +02:00
Glenn Jocher 464c2c6713
Colab and Kaggle loggers removeHandler (#8985) 
Resolve duplicate outputs in colab. Also optimizes Colab and Kaggle environment checks.

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-16 16:49:32 +02:00
Glenn Jocher d5f543a1df Created using Colaboratory 2022-08-16 13:36:37 +02:00
Glenn Jocher 1f5a28711d Created using Colaboratory 2022-08-16 13:33:59 +02:00
Michel Promonet 4d05472d2b
Allow multiple-model serving from Flask REST API (#8973) 
* allow to serve multiple models using flask restapi

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

* Update restapi.py

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>
 2022-08-15 23:42:25 +02:00
Glenn Jocher d7bc5d7773
Add `.tar` support for datasets (#8963) 2022-08-14 23:06:42 +02:00
Glenn Jocher 3fc89994e9 Created using Colaboratory 2022-08-14 22:50:51 +02:00
Glenn Jocher 42812fcb18
Add bash script arguments (#8962) 2022-08-14 22:33:55 +02:00
Glenn Jocher 7639e4c7ef
Fix windows LOGGER with emojis output (#8958) 
* Fix duplicate LOGGER output

* Update general.py
 2022-08-14 00:12:09 +02:00
Glenn Jocher dc38cd03f4
New `smart_inference_mode()` conditional decorator (#8957) 
New smart_inference_mode()
 2022-08-13 20:38:51 +02:00
Glenn Jocher 6aed0a7c00
GFLOPs computation fix for classification models (#8954) 
* GFLOPs computation fix for classification models

Improved robustness in reading input channel count

* Update torch_utils.py

* Update torch_utils.py
 2022-08-13 16:38:11 +02:00
Glenn Jocher f1214f237d
Remove DDP `destroy_process_group()` on train end (#8935) 
May resolve https://github.com/ultralytics/yolov5/issues/7307
 2022-08-13 03:57:31 +02:00
Kalen Michael 11a76bb4f5
Allow train to use zipped content (#8940) 
* fix: added transparent image and empty alt to social bar

* fix: remove underlines

* fix: hide underlines for all social links

* fix: always unzip into folder
 2022-08-13 03:39:09 +02:00
Glenn Jocher 2e57b8418d
Deci.ai updates (#8928) 
* Deci.ai updates

Content implementation for https://deci.ai/

* Update README.md

* Update README.md

* Update README.md
 2022-08-11 00:01:38 +02:00
Glenn Jocher 259e055b42
Fix `--source 'path/*.jpg'` glob example (#8927) 
* Fix `--source 'path/*.jpg'` glob example

* Update README_cn.md

* Update tutorial.ipynb
 2022-08-10 21:53:12 +02:00
Glenn Jocher 4c6bdbfcde
Direct download table links (#8917) 
* Direct download table links

Per recent partner feedback

* Update README_cn.md

* Update README_cn.md

* Update README.md

* Update README_cn.md

* Update README.md
 2022-08-10 17:01:01 +02:00
Glenn Jocher 3d47fc6c55
Update README.md 2022-08-10 13:10:30 +02:00
Glenn Jocher e242ede14c
Add `torch==1.7.0` to CI tests (#8916) 
* Add torch==1.7.0 to CI tests

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Attempt crash on 1.7.0

* revert crash

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml
 2022-08-09 23:46:30 +02:00
Glenn Jocher 7ab1f50633
Scope `torchvision.utils.draw_bounding_boxes` import (#8915) 
* Scope `torchvision.utils.draw_bounding_boxes` import

Quick fix for https://github.com/ultralytics/yolov5/issues/8898#issuecomment-1208851874 until a more permanent fix is implemented

* Update clearml_utils.py
 2022-08-09 20:29:25 +02:00
Code-Bat b551098d59
About "os.R_OK" in general.py (#8909) 
The notes says "Return True if directory has write permissions", however, the code below is "os.R_OK", I think "os.W_OK" is preferred.
 2022-08-09 16:59:36 +02:00
Glenn Jocher f5335f22bb
Capitalize YouTube (#8903) 2022-08-08 20:36:18 +02:00
Glenn Jocher 4bb305275a
Edge TPU add `--search_delegate` fix (#8902) 
Resolves https://github.com/ultralytics/yolov5/issues/8842
 2022-08-08 17:51:28 +02:00
黄不盈 c962db2749
Fix anchor incorrectly initialized (#8891) 
* Fix anchor incorrectly initialized

Using --noautoanchor and --evolve simultaneously leads to anchor incorrectly initialized. --noautoanchor denotes anchors don't need to evolve, thus removing anchors from hyp will fix it.

* Update train.py

* Update train.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-08 17:15:18 +02:00
Glenn Jocher 48a85314bc
Update README.md Environments icons (#8895) 2022-08-07 14:51:30 +02:00
Kalen Michael 0d8546a01f
Fix/improve social media bar (#8893) 
* fix: added transparent image and empty alt to social bar

* fix: remove underlines

* fix: hide underlines for all social links

* Update image URLs to ultralytics/assets

* Update bottom 3% icons

* Update README.md

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-07 14:04:39 +02:00
Glenn Jocher fcfaf0a29b
Update README_cn.md 2022-08-07 14:04:06 +02:00
Glenn Jocher 8f28ea4945
emoji-safe default logging (#8888) 
* emoji-safe default logging

* implement everywhere
 2022-08-06 12:30:08 +02:00
Glenn Jocher 73ed7a5e7a Created using Colaboratory 2022-08-06 11:53:29 +02:00
Glenn Jocher d631a6904e Created using Colaboratory 2022-08-06 11:44:52 +02:00
Glenn Jocher 20f1b7ea08
`smart_optimizer()` improved reporting (#8887) 
Update smart_optimizer() weight_decay reporting
 2022-08-06 11:30:54 +02:00
Glenn Jocher 030586a31c Created using Colaboratory 2022-08-06 01:14:31 +02:00
Glenn Jocher 5a0faef353 Created using Colaboratory 2022-08-06 01:10:17 +02:00
Victor Sonck 378bde4bba
ClearML experiment tracking integration (#8620) 
* Add titles to matplotlib plots

* Add ClearML Experiment Tracking integration.

* Add ClearML Data Version Management automatic download when requested

* Add ClearML Hyperparameter Optimization

* ClearML save period integration

* Fix wandb breaking when used with ClearML dataset

* Fix wandb breaking when used with ClearML resume and dataset

* Add ClearML documentation

* fixed small bug in clearml integration that misreports epoch number

* Final ClearMl additions before refactor

* Add correct epoch reporting

* Add remote execution and autoscaling docs for ClearML integration

* Added images to clearml integration docs

* fixed logo alignment bug and added hpo screenshot clearml

* Fixed small epoch number bug in clearml integration

* Remove saved model flush clearml

* Cleanup clearml readme section

* Cleaned up clearml logger docstring

* Remove resume readme section clearml

* Clearml integration cleanup

* Updated ClearML documentation

* Added dark vs light icons ClearML Readme

* Clearml Readme styling

* Add better gifs

* Fixed gif file size

* Add better images in tutorial notebook

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Addressed comments in PR #8620

* Fixed circular import

* Fixed circular import

* Update tutorial.ipynb

* Update tutorial.ipynb

* Inline comment

* Restructured tutorial notebook

* Add correct ClearML link to README

* Update tutorial.ipynb

* Update general.py

* Update __init__.py

* Update __init__.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update __init__.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update __init__.py

* Update README.md

* Update __init__.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* spelling

* Update tutorial.ipynb

* notebook cutt.ly links

* Update README.md

* Update README.md

* cutt.ly links in tutorial

* Removed labels as they show up on last subplot only

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>
 2022-08-05 20:50:49 +02:00
Glenn Jocher 2794483e09
Update CI to default Python 3.10 (#8883) 
* Update CI to default Python 3.10

* Update ci-testing.yml

* Update ci-testing.yml
 2022-08-05 17:10:44 +02:00
Glenn Jocher daed7a844e
`--resume` training from URL weights fix (#8884) 
--resume training from URL weights fix

@kalenmike should fix data error on HUB resume
 2022-08-05 16:42:10 +02:00
Glenn Jocher e073658e11
`--resume` training from URL weights (#8882) 
@kalenmike
 2022-08-05 16:27:28 +02:00
Glenn Jocher bc9fcb1767
HUBDatasetStats() preview images to 50 quality (#8880) 
@kalenmike should represent a 30% filesize reduction vs 75 quality
 2022-08-05 14:45:41 +02:00
Glenn Jocher 731a2f8c1f
Single-line TRT dynamic assertion (#8871) 2022-08-04 23:34:15 +02:00
Glenn Jocher 38a6eb6e99
Fix TensorRT --dynamic excess outputs bug (#8869) 
* Fix TensorRT --dynamic excess outputs bug

Potential fix for https://github.com/ultralytics/yolov5/issues/8790

* Cleanup

* Update common.py

* Update common.py

* New fix
 2022-08-04 23:26:30 +02:00
Glenn Jocher 84e7748564
Update dataloaders.py remove `float64` shapes (#8865) 
May help https://github.com/ultralytics/yolov5/issues/8862
 2022-08-04 17:06:08 +02:00
Glenn Jocher 628c05ca6f
export.py replace `check_file` -> `check_yaml` (#8852) 
* export.py replace `check_file` -> `check_yaml`

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-03 23:38:36 +02:00
Glenn Jocher 6884da3a32
Add check_file(data) i.e. `--data coco128.yaml` (#8851) 
* Add check_file(data) i.e. `--data coco128.yaml`

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-03 23:32:31 +02:00