ba6f3f974b
Enable direct `--weights URL` definition ( #3373 )
* Enable direct `--weights URL` definition
@KalenMike this PR will enable direct --weights URL definition. Example use case:
```
python train.py --weights https://storage.googleapis.com/bucket/dir/model.pt
```
* cleanup
* bug fixes
* weights = attempt_download(weights)
* Update experimental.py
* Update hubconf.py
* return bug fix
* comment mirror
* min_bytes
3 lat temu
ef4d53818d
ONNX export in .train() mode fix ( #3362 )
3 lat temu
1f8d716ec9
yolo.py header ( #3347 )
3 lat temu
7b36e38cf8
Check CoreML models.train() mode ( #3262 )
* Check CoreML models.train() mode
* Update export.py
3 lat temu
3f74cd9ed1
Parameterize max_det + inference default at 1000 ( #3215 )
* Added max_det parameters in various places
* 120 character line
* PEP8
* 120 character line
* Update inference default to 1000 instances
* Update inference default to 1000 instances
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
9ab561dbfc
Parameterize ONNX `--opset-version` ( #3154 )
3 lat temu
be86c21c73
rename class autoShape -> AutoShape ( #3173 )
* rename class autoShape -> AutoShape
follow other class naming convention
* rename class autoShape -> AutoShape
follow other classes' naming convention
* rename class autoShape -> AutoShape
3 lat temu
d9b4e6b748
Add `--include torchscript onnx coreml` argument ( #3137 )
* Allow users to skip exporting in formats that they don't care about
* Correct comments
* Update export.py
renamed --skip-format to --exclude
* Switched format from exclude to include (as instructed by @glenn-jocher )
* cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
525f4f86a9
Add --optimize argument ( #3093 )
Fix for c++ runtime errors in https://github.com/ultralytics/yolov5/issues/2973
3 lat temu
251aeafcb1
Update P5 + P6 model ensembling ( #3082 )
3 lat temu
e97d129db4
Update export.py with --train mode argument ( #3066 )
3 lat temu
3ef3a95cfa
Do not optimize CoreML TorchScript model ( #3055 )
3 lat temu
b292837e36
Fix ONNX export using --grid --simplify --dynamic simultaneously ( #2982 )
* Update yolo.py
* Update export.py
* fix export grid
* Update export.py, remove detect export attribute
* rearrange if order
* remove --grid, default inplace=False
* rename exp_dynamic to onnx_dynamic, comment
* replace bs with 1 in anchor_grid[i] index 0
* Update export.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
e2a80c6c0f
Add support for FP16 (half) to export.py ( #3010 )
* Added support for fp16 (half) to export.py
* minimize code additions
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
41f5cc5637
YOLOv5 AWS Inferentia Inplace compatibility updates ( #2953 )
* Added flag to enable/disable all inplace and assignment operations
* Removed shape print statements
* Scope Detect/Model import to avoid circular dependency
* PEP8
* create _descale_pred()
* replace lost space
* replace list with tuple
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
57812df68c
New Colors() class ( #2963 )
3 lat temu
4200674a13
Add yolov5/ to sys.path() for *.py subdir exec ( #2949 )
* Add yolov5/ to sys.path() for *.py subdir exec
* Update export.py
3 lat temu
4890499344
Improved yolo.py profiling ( #2940 )
* Improved yolo.py profiling
Improved column order and labelling.
* Update yolo.py
3 lat temu
c0d3f80544
Add verbose option to pytorch hub models ( #2926 )
* Add verbose and update print to logging
* Fix positonal param
* Revert auto formatting changes
* Update hubconf.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
1b1ab4cca2
Add file_size() function ( #2911 )
* Add file_size() function
* Update export.py
3 lat temu
646386ff09
Update export.py for 2 dry runs ( #2910 )
* Update export.py for 2 dry runs
* Update export.py
3 lat temu
a2a514dec8
Update export.py ( #2909 )
3 lat temu
28db237639
Default optimize_for_mobile() on TorchScript models ( #2908 )
Per https://pytorch.org/tutorials/recipes/script_optimized.html this should improve performance on torchscript models (and maybe coreml models also since coremltools operates on a torchscript model input, though this still requires testing).
3 lat temu
cdb678f418
Update yolo.py ( #2899 )
3 lat temu
f7bc685c2c
Implement yaml.safe_load() ( #2876 )
* Implement yaml.safe_load()
* yaml.safe_dump()
3 lat temu
c949fc86d1
Detection cropping+saving feature addition for detect.py and PyTorch Hub ( #2827 )
* Update detect.py
* Update detect.py
* Update greetings.yml
* Update cropping
* cleanup
* Update increment_path()
* Update common.py
* Update detect.py
* Update detect.py
* Update detect.py
* Update common.py
* cleanup
* Update detect.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
1df8c6c963
Fix ONNX dynamic axes export support with onnx simplifier, make onnx simplifier optional ( #2856 )
* Ensure dynamic export works succesfully, onnx simplifier optional
* Update export.py
* add dashes
Co-authored-by: Tim <tim.stokman@hal24k.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
c15e25c40f
PyTorch Hub cv2 .save() .show() bug fix ( #2831 )
* PyTorch Hub cv2 .save() .show() bug fix
cv2.rectangle() was failing on non-contiguous np array inputs. This checks for contiguous arrays and applies is necessary:
```python
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
```
* Update plots.py
```python
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to plot_on_box() input image.'
```
* Update hubconf.py
Expand CI tests to OpenCV image.
3 lat temu
1f3e482bce
ONNX Simplifier ( #2815 )
* ONNX Simplifier
Add ONNX Simplifier to ONNX export pipeline in export.py. Will auto-install onnx-simplifier if onnx is installed but onnx-simplifier is not.
* Update general.py
3 lat temu
0f395b3e3b
YOLOv5 v5.0 Release patch 1 ( #2764 )
* torch.jit.trace(model, img, strict=False)
* Update check_file()
* Update hubconf.py
* Update README.md
3 lat temu
b5de52c4cd
torch.cuda.amp bug fix ( #2750 )
PR https://github.com/ultralytics/yolov5/pull/2725 introduced a very specific bug that only affects multi-GPU trainings. Apparently the cause was using the torch.cuda.amp decorator in the autoShape forward method. I've implemented amp more traditionally in this PR, and the bug is resolved.
3 lat temu
fca5e2a48f
autocast enable=torch.cuda.is_available() ( #2748 )
3 lat temu
c03d590320
Add Hub results.pandas() method ( #2725 )
* Add Hub results.pandas() method
New method converts results from torch tensors to pandas DataFrames with column names.
This PR may partially resolve issue https://github.com/ultralytics/yolov5/issues/2703
```python
results = model(imgs)
print(results.pandas().xyxy[0])
xmin ymin xmax ymax confidence class name
0 57.068970 391.770599 241.383545 905.797852 0.868964 0 person
1 667.661255 399.303589 810.000000 881.396667 0.851888 0 person
2 222.878387 414.774231 343.804474 857.825073 0.838376 0 person
3 4.205386 234.447678 803.739136 750.023376 0.658006 5 bus
4 0.000000 550.596008 76.681190 878.669922 0.450596 0 person
```
* Update comments
torch example input now shown resized to size=640 and also now a multiple of P6 stride 64 (see https://github.com/ultralytics/yolov5/issues/2722#issuecomment-814785930 )
* apply decorators
* PEP8
* Update common.py
* pd.options.display.max_columns = 10
* Update common.py
3 lat temu
ec8979f1d2
Updated filename attributes for YOLOv5 Hub BytesIO ( #2718 )
Fix 2 for 'Model predict with forward will fail if PIL image does not have filename attribute' #2702
3 lat temu
74276d5189
Updated filename attributes for YOLOv5 Hub results ( #2708 )
Proposed fix for 'Model predict with forward will fail if PIL image does not have filename attribute' #2702
3 lat temu
17300a4c7b
autoShape forward im = np.asarray(im) # to numpy ( #2689 )
Slight speedup.
3 lat temu
2af059c0d8
PyTorch Hub model.save() increment as runs/hub/exp ( #2684 )
* PyTorch Hub model.save() increment as runs/hub/exp
This chane will align PyTorch Hub results saving with the existing unified results saving directory structure of
runs/
/train
/detect
/test
/hub
/exp
/exp2
...
* cleanup
3 lat temu
1148e2ea63
Add TransformerLayer, TransformerBlock, C3TR modules ( #2333 )
* yolotr
* transformer block
* Remove bias in Transformer
* Remove C3T
* Remove a deprecated class
* put the 2nd LayerNorm into the 2nd residual block
* move example model to models/hub, rename to -transformer
* Add module comments and TODOs
* Remove LN in Transformer
* Add comments for Transformer
* Solve the problem of MA with DDP
* cleanup
* cleanup find_unused_parameters
* PEP8 reformat
Co-authored-by: DingYiwei <846414640@qq.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
2bf34f50fd
PyTorch Hub amp.autocast() inference ( #2641 )
I think this should help speed up CUDA inference, as currently models may be running in FP32 inference mode on CUDA devices unnecesarily.
3 lat temu
005d7a8c54
Update Detections() self.n comment ( #2620 )
```python
self.n = len(self.pred) # number of images (batch size)
```
3 lat temu
a57f23d18b
Update detections() self.t = tuple() ( #2617 )
* Update detections() self.t = tuple()
Fix multiple results.print() bug.
* Update experimental.py
* Update yolo.py
3 lat temu
1c132a1f94
Update Detections() times=None ( #2570 )
Fix for results.tolist() method breaking after YOLOv5 Hub profiling PRshttps://github.com/ultralytics/yolov5/pull/2460 https://github.com/ultralytics/yolov5/pull/2459 and
3 lat temu
e8fc97aa38
Improved W&B integration ( #2125 )
* Init Commit
* new wandb integration
* Update
* Use data_dict in test
* Updates
* Update: scope of log_img
* Update: scope of log_img
* Update
* Update: Fix logging conditions
* Add tqdm bar, support for .txt dataset format
* Improve Result table Logger
* Init Commit
* new wandb integration
* Update
* Use data_dict in test
* Updates
* Update: scope of log_img
* Update: scope of log_img
* Update
* Update: Fix logging conditions
* Add tqdm bar, support for .txt dataset format
* Improve Result table Logger
* Add dataset creation in training script
* Change scope: self.wandb_run
* Add wandb-artifact:// natively
you can now use --resume with wandb run links
* Add suuport for logging dataset while training
* Cleanup
* Fix: Merge conflict
* Fix: CI tests
* Automatically use wandb config
* Fix: Resume
* Fix: CI
* Enhance: Using val_table
* More resume enhancement
* FIX : CI
* Add alias
* Get useful opt config data
* train.py cleanup
* Cleanup train.py
* more cleanup
* Cleanup| CI fix
* Reformat using PEP8
* FIX:CI
* rebase
* remove uneccesary changes
* remove uneccesary changes
* remove uneccesary changes
* remove unecessary chage from test.py
* FIX: resume from local checkpoint
* FIX:resume
* FIX:resume
* Reformat
* Performance improvement
* Fix local resume
* Fix local resume
* FIX:CI
* Fix: CI
* Imporve image logging
* (:(:Redo CI tests:):)
* Remember epochs when resuming
* Remember epochs when resuming
* Update DDP location
Potential fix for #2405
* PEP8 reformat
* 0.25 confidence threshold
* reset train.py plots syntax to previous
* reset epochs completed syntax to previous
* reset space to previous
* remove brackets
* reset comment to previous
* Update: is_coco check, remove unused code
* Remove redundant print statement
* Remove wandb imports
* remove dsviz logger from test.py
* Remove redundant change from test.py
* remove redundant changes from train.py
* reformat and improvements
* Fix typo
* Add tqdm tqdm progress when scanning files, naming improvements
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
f813f6dcc8
autoShape() speed profiling update ( #2460 )
3 lat temu
569757ecc0
Add autoShape() speed profiling ( #2459 )
* Add autoShape() speed profiling
* Update common.py
* Create README.md
* Update hubconf.py
* cleanuip
3 lat temu
7a0a81fd1d
GPU export options ( #2297 )
* option for skip last layer and cuda export support
* added parameter device
* fix import
* cleanup 1
* cleanup 2
* opt-in grid
--grid will export with grid computation, default export will skip grid (same as current)
* default --device cpu
GPU export causes ONNX and CoreML errors.
Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 lat temu
a3ecf0fd64
Anchor override ( #2350 )
3 lat temu
fab5085674
EMA bug fix 2 ( #2330 )
* EMA bug fix 2
* update
3 lat temu
fd96810518
remove TTA 1 pixel offset ( #2325 )
3 lat temu
cbd55da5d2
Update yolo.py ( #2120 )
* Avoid mutable state in Detect
* LoadImages() pathlib update (#2140 )
* Unique *.cache filenames fix (#2134 )
* fix #2121
* Update test.py
* Update train.py
* Update autoanchor.py
* Update datasets.py
* Update log_dataset.py
* Update datasets.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Update train.py test batch_size (#2148 )
* Update train.py
* Update loss.py
* Update train.py (#2149 )
* Linear LR scheduler option (#2150 )
* Linear LR scheduler option
* Update train.py
* Update data-autodownload background tasks (#2154 )
* Update get_coco.sh
* Update get_voc.sh
* Update detect.py (#2167 )
Without this cv2.imshow opens a window but nothing is visible
* Update requirements.txt (#2173 )
* Update utils/datasets.py to support .webp files (#2174 )
Simply added 'webp' as an image format to the img_formats array so that webp image files can be used as training data.
* Changed socket port and added timeout (#2176 )
* PyTorch Hub results.save('path/to/dir') (#2179 )
* 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
* Created using Colaboratory
* YOLOv5 PyTorch Hub results.save() method retains filenames (#2194 )
* save results with name
* debug
* save original imgs names
* Update common.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* TTA augument boxes one pixel shifted in de-flip ud and lr (#2219 )
* TTA augument boxes one pixel shifted in de-flip ud and lr
* PEP8 reformat
Co-authored-by: Jaap van de Loosdrecht <jaap.van.de.loosdrecht@nhlstenden.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* LoadStreams() frame loss bug fix (#2222 )
* Update yolo.py channel array (#2223 )
* Add check_imshow() (#2231 )
* Add check_imshow()
* Update general.py
* Update general.py
* Update CI badge (#2230 )
* Add isdocker() (#2232 )
* Add isdocker()
* Update general.py
* Update general.py
* YOLOv5 Hub URL inference bug fix (#2250 )
* Update common.py
* Update common.py
* Update common.py
* Improved hubconf.py CI tests (#2251 )
* Unified hub and detect.py box and labels plotting (#2243 )
* reset head
* Update inference default to multi_label=False (#2252 )
* Update inference default to multi_label=False
* bug fix
* Update plots.py
* Update plots.py
* Robust objectness loss balancing (#2256 )
* Created using Colaboratory
* Update minimum stride to 32 (#2266 )
* Dynamic ONNX engine generation (#2208 )
* add: dynamic onnx export
* delete: test onnx inference
* fix dynamic output axis
* Code reduction
* fix: dynamic output axes, dynamic input naming
* Remove fixed axes
Co-authored-by: Shivam Swanrkar <ss8464@nyu.edu>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Update greetings.yml for auto-rebase on PR (#2272 )
* Update Dockerfile with apt install zip (#2274 )
* FLOPS min stride 32 (#2276 )
Signed-off-by: xiaowo1996 <429740343@qq.com>
* Update README.md
* Amazon AWS EC2 startup and re-startup scripts (#2185 )
* Amazon AWS EC2 startup and re-startup scripts
* Create resume.py
* cleanup
* Amazon AWS EC2 startup and re-startup scripts (#2282 )
* Update train.py (#2290 )
* Update train.py
* Update train.py
* Update train.py
* Update train.py
* Create train.py
* Improved model+EMA checkpointing (#2292 )
* Enhanced model+EMA checkpointing
* update
* bug fix
* bug fix 2
* always save optimizer
* ema half
* remove model.float()
* model half
* carry ema/model in fp32
* rm model.float()
* both to float always
* cleanup
* cleanup
* Improved model+EMA checkpointing 2 (#2295 )
* Fix labels being missed when image extension appears twice in filename (#2300 )
* W&B entity support (#2298 )
* W&B entity support
* shorten wandb_entity to entity
Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Avoid mutable state in Detect
* Update yolo and remove .to(device)
Co-authored-by: Oleg Boiko <oboiko@chegg.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: train255 <thanhdd.it@gmail.com>
Co-authored-by: ab-101 <56578530+ab-101@users.noreply.github.com>
Co-authored-by: Transigent <wbdsmith@optusnet.com.au>
Co-authored-by: NanoCode012 <kevinvong@rocketmail.com>
Co-authored-by: Daniel Khromov <danielkhromov@gmail.com>
Co-authored-by: VdLMV <jaap@vdlmv.nl>
Co-authored-by: Jaap van de Loosdrecht <jaap.van.de.loosdrecht@nhlstenden.com>
Co-authored-by: Yann Defretin <kinoute@gmail.com>
Co-authored-by: Aditya Lohia <64709773+aditya-dl@users.noreply.github.com>
Co-authored-by: Shivam Swanrkar <ss8464@nyu.edu>
Co-authored-by: xiaowo1996 <429740343@qq.com>
Co-authored-by: Iden Craven <iden.craven@gmail.com>
Co-authored-by: Jan Hajek <toretak@users.noreply.github.com>
Co-authored-by: Jan Hajek <jan.hajek@gmail.com>
3 lat temu
Glenn Jocher
WangChaofeng
Adrian Holovaty
Cristi Fati
Yonghye Kwon
jylink
Hodovo
jluntamazon
NanoCode012
Burhan
Tim Stokman
Ding Yiwei
Ayush Chaurasia
Jan Hajek
oleg