Ankle/yolov5_birdproject
1
0 Fork 0
Code Issues Pull Requests Actions 3 Packages Projects Releases Wiki Activity
2,263 Commits 1 Branch 0 Tags
eab35f66f9104992a448fbd726c6c2dfdfdf240f
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Glenn Jocher eab35f66f9 Install torch latest stable (#9092) 
Install torch 1.12.1 stable 

GPU assignment issues in 1.13 nightly that comes with image

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-22 22:18:01 +02:00
Glenn Jocher 06831aa9e9 Improved Usage example docstrings (#9075) 
* Updated Usage examples

* Update detect.py

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

* Update predict.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-22 01:06:29 +02:00
Glenn Jocherandpre-commit-ci[bot] 0abae780b3 Remove unused Timeout import (#9073) 
* Remove unused Timeout import

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

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

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-22 00:04:30 +02:00
Glenn Jocherandpre-commit-ci[bot] 262187e95d Two dimensional size=(h,w) AutoShape support (#9072) 
* Two dimensional `size=(h,w)` AutoShape support

May resolve https://github.com/ultralytics/yolov5/issues/9039

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

* Update hubconf.py

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

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

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-21 23:26:07 +02:00
Glenn Jocher db2ee5fa0c De-thread TensorBoard graph logging (#9071) 
* De-thread TensorBoard graph logging

Issues with Classification models

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

* Update __init__.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-21 17:07:56 +02:00
Glenn Jocher 5373a28c1b Created using Colaboratory 2022-08-21 17:01:05 +02:00
Glenn Jocher 8665d557c1 Threaded TensorBoard graph logging (#9070) 
* Log TensorBoard graph on pretrain_routine_end

* fix
 2022-08-21 16:51:50 +02:00
Glenn Jocher 0b8639a40a Rename 'labels' to 'instances' (#9066) 
* Rename labels to instances

* Rename labels to instances

* align val
 2022-08-21 15:50:02 +02:00
Glenn Jocher e6b4bf0bc2 Created using Colaboratory 2022-08-21 14:21:48 +02:00
Glenn Jocher 1499526f56 Created using Colaboratory 2022-08-21 14:20:12 +02:00
Glenn Jocher 794f117f4b Created using Colaboratory 2022-08-21 13:33:13 +02:00
Glenn Jocher 6077bf032a TensorBoard fix in tutorial.ipynb (#9064) 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-21 13:10:02 +02:00
Glenn Jocherandpre-commit-ci[bot] e0700cce77 Daemon plot_labels() for faster start (#9057) 
* Daemon `plot_labels()` for faster start

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

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

* Update train.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-21 03:47:37 +02:00
Glenn Jocherandpre-commit-ci[bot] 27fb6fd8fc zero-mAP fix 3 (#9058) 
* zero-mAP fix 3

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

* Update torch_utils.py

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

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

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

* Update torch_utils.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-21 03:22:24 +02:00
Glenn Jocher 841f312f93 zero-mAP fix return .detach() to EMA (#9056) 
Resolves https://github.com/ultralytics/hub/issues/82

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-21 02:23:39 +02:00
Glenn Jocher 93f63ee33f Refactor for simplification 2 (#9055) 
* Refactor for simplification 2

* Update __init__.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-21 02:00:35 +02:00
Glenn Jocherandpre-commit-ci[bot] c725511bfc Refactor for simplification (#9054) 
* Refactor for simplification

* cleanup

* [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>
 2022-08-21 01:34:03 +02:00
Glenn Jocher f258cf8b37 Add --save-hybrid mAP warning (#9050) 
* Add `--save-hybrid` mAP warning

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

* Update val.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-20 17:17:35 +02:00
Glenn Jocher fc8758a49b Temporarily remove macos-latest from CI (#9049) 
* Temporarily remove macos-latest from CI

macos-latest causing many failed CI runs that resolve after manually re-running 2 or 3 times. I don't know what the cause is. Will replace at a later date.

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

* Update ci-testing.yml

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-20 16:45:11 +02:00
Glenn Jocherandpre-commit-ci[bot] a409ec7953 AutoBatch protect from negative batch sizes (#9048) 
* AutoBatch protect from negative batch sizes

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

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

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

* cleanup

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

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-20 16:29:08 +02:00
Glenn Jocher ba1c6773c2 Created using Colaboratory 2022-08-19 18:41:30 +02:00
Glenn Jocher aed88848a2 Simplified notebook 2022-08-19 18:00:38 +02:00
Glenn Jocherandpre-commit-ci[bot] fdcb92a938 Update train.py import val as validate (#9037) 
* Update train.py `import val as validate`

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

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

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-19 16:54:58 +02:00
Glenn Jocher 4a8ab3bc42 VOC names dictionary fix (#9034) 
* VOC names dictionary fix

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

* Update dataloaders.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-19 15:07:04 +02:00
Glenn Jocher 781401ec70 Default --data imagenette160 training (fastest) (#9033) 
* Default --data `imagenette160` training (fastest)

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

* Update train.py

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

* Update train.py

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

* Update train.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-19 15:06:37 +02:00
Glenn Jocher 1cd3e752de Created using Colaboratory 2022-08-19 02:01:40 +02:00
Glenn Jocher 840b7232db Attach transforms to model (#9028) 
* Attach transforms to model

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

* Update val.py

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

* Update train.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-19 01:59:51 +02:00
Glenn Jocher 4bc5520e94 Created using Colaboratory 2022-08-19 01:30:14 +02:00
Glenn Jocher eb359c3a22 Add PyTorch Hub classification CI checks (#9027) 
* Add PyTorch Hub classification CI checks

Add PyTorch Hub loading of official and custom trained classification models to CI checks. 

May help resolve https://github.com/ultralytics/yolov5/issues/8790#issuecomment-1219840718

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

* Update hubconf.py

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-18 21:45:11 +02:00
Glenn Jocher a5a47c52ca Remove unused time_sync import (#9026) 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-18 20:26:18 +02:00
Glenn Jocher de6e6c0110 Created using Colaboratory 2022-08-18 20:23:14 +02:00
Glenn Jocher 61adf017f2 torch.empty() for speed improvements (#9025) 
`torch.empty()` for speed improvement

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-18 20:12:33 +02:00
Glenn Jocherandpre-commit-ci[bot] d40cd0d454 Improved Profile() inference timing (#9024) 
* Improved `Profile()` class

* Update predict.py

* Update val.py

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

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

* Update val.py

* Update AutoShape

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-18 19:55:38 +02:00
Glenn Jocher 20049be2e7 EMA FP32 assert classification bug fix (#9016) 
* Return EMA float on classification val

* verbose val fix

* EMA check
 2022-08-18 14:06:15 +02:00
Glenn Jocherandpre-commit-ci[bot] 529aafd737 Fix TorchScript JSON string key bug (#9015) 
* Fix TorchScript JSON string key bug

Resolves https://github.com/ultralytics/yolov5/issues/9011

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

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

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

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-18 11:50:24 +02:00
glennjocher 5c854fab5e requires grad after reset params 2022-08-18 02:44:50 +02:00
Glenn Jocher e08d568d39 Add glob quotes to detect.py usage example (#9007) 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-18 01:08:52 +02:00
Glenn Jocher 6728dad76d Add weight decay to argparser (#9006) 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-17 22:57:55 +02:00
Glenn Jocher 0922bc2082 DockerHub tag update Usage example (#9005) 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
 2022-08-17 22:50:08 +02:00
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
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 Jocherpre-commit-ci[bot]Ayush Chaurasia
 		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
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
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
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
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
Glenn Jocher 48a85314bc Update README.md Environments icons (#8895) 2022-08-07 14:51:30 +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
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 Jocherandpre-commit-ci[bot] 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 Jocherandpre-commit-ci[bot] 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
Glenn Jocherandpre-commit-ci[bot] a75a1105a1 Self-contained checkpoint --resume (#8839) 
* Single checkpoint resume

* Update train.py

* Add hyp

* Add hyp

* Add hyp

* FIX

* avoid resume on url data

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

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

* avoid resume on url data

* avoid resume on url data

* Update

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-08-03 21:28:22 +02:00
Glenn Jocher 4d8d84b0ea Created using Colaboratory 2022-08-03 12:49:02 +02:00
Glenn Jocher e5991c9867 Created using Colaboratory 2022-08-03 00:57:40 +02:00
Glenn Jocher 08c8c3e00a New smart_resume() (#8838) 
* New `smart_resume()`

* Update torch_utils.py

* Update torch_utils.py

* Update torch_utils.py

* fix
 2022-08-02 15:13:58 +02:00
Glenn Jocher ba140e5685 RUN git clone instead of COPY to /usr/src/app (#8827) 
Update
 2022-08-01 21:45:31 +02:00
Glenn Jocher f3c78a387e Remove hook torch.nan_to_num(x) (#8826) 
* Remove hook `torch.nan_to_num(x)`

Observed erratic training behavior (green line) with the nan_to_num hook in classifier branch. I'm going to remove it from master.

* Update train.py
 2022-08-01 21:39:04 +02:00
Glenn Jocherandpre-commit-ci[bot] 59578f2782 Update README.md with contributors.png (#8820) 
* Update README.md with contributors.png

Replace dynamic svg from opencollective with static png for improved stability and lighter size (400kB vs 2MB).

@AyushExel

* Update README.md

* Update README.md

* Update README_cn.md

* [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>
 2022-08-01 20:28:24 +02:00
Glenn Jocher 7b9cc3205a Add .git to .dockerignore (#8815) 2022-08-01 03:33:28 +02:00
Glenn Jocher 39ce8ca19a Remove assert not is_docker() from GitHub checks (#8813) 
* Update

* Update
 2022-08-01 03:01:44 +02:00
Glenn Jocherandpre-commit-ci[bot] 6717519635 Update .pre-commit-config.yaml (#8812) 
* Update .pre-commit-config.yaml

Comment EOF fixer

* [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>
 2022-08-01 02:09:36 +02:00
Glenn Jocher 0e165c50f7 Created using Colaboratory 2022-07-31 20:34:03 +02:00
Glenn Jocher 685332ede4 Update .pre-commit-config.yaml (#8811) 2022-07-31 20:06:35 +02:00
Glenn Jocher 40c41e4269 Fix Colab-update pre-commit EOF bug (#8810) 2022-07-31 19:57:40 +02:00
Glenn Jocher 7b72d9a607 Update ci-testing.yml streamlined tests (#8809) 
* Update ci-testing.yml streamlined tests

* Update ci-testing.yml

* Update ci-testing.yml
 2022-07-31 16:12:32 +02:00
Glenn Jocher 555976b346 FROM nvcr.io/nvidia/pytorch:22.07-py3 (#8808) 2022-07-31 15:23:57 +02:00
Glenn Jocher 9559601b9a Update requirements.txt with tf-cpu and tf-aarch64 (#8807) 2022-07-31 14:54:55 +02:00
Glenn Jocher 34cb277dc5 Fix val.py 'no labels found bug' (#8806) 
Resolves https://github.com/ultralytics/yolov5/issues/8791

Bug first introduced in #8782
 2022-07-31 14:17:23 +02:00
Glenn Jocher 59595c1365 Update train.py for val.run(half=amp) (#8804) 
Disable FP16 validation if AMP checks fail or amp=False.
 2022-07-31 04:17:39 +02:00
Glenn Jocher 1e89807d9a Detect.inplace=False for multithread-safe inference (#8801) 
Detect.inplace=False for safe multithread inference
 2022-07-30 22:19:40 +02:00
Glenn Jocher 7921351b4e Deprecate torch 1.6.0 compat _non_persistent_buffers_set (#8797) 
Deprecate torch 1.6.0 compat _non_persistent_buffers_set
 2022-07-30 21:25:16 +02:00