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.
2021-04-09 18:19:49 +02:00
fca5e2a48f
autocast enable=torch.cuda.is_available() ( #2748 )
2021-04-09 13:34:49 +02:00
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
2021-04-07 16:28:07 +02:00
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
2021-04-06 13:18:56 +02:00
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
2021-04-05 22:20:09 +02:00
17300a4c7b
autoShape forward im = np.asarray(im) # to numpy ( #2689 )
...
Slight speedup.
2021-04-02 12:36:38 +02:00
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
2021-04-02 11:55:10 +02:00
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>
2021-04-01 17:26:53 +02:00
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.
2021-03-28 20:23:40 +02:00
005d7a8c54
Update Detections() self.n comment ( #2620 )
...
```python
self.n = len(self.pred) # number of images (batch size)
```
2021-03-26 21:19:15 +01:00
a57f23d18b
Update detections() self.t = tuple() ( #2617 )
...
* Update detections() self.t = tuple()
Fix multiple results.print() bug.
* Update experimental.py
* Update yolo.py
2021-03-26 13:23:11 +01:00
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
2021-03-23 14:10:47 +01:00
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>
2021-03-23 00:44:50 +01:00
f813f6dcc8
autoShape() speed profiling update ( #2460 )
2021-03-13 20:00:03 -08:00
569757ecc0
Add autoShape() speed profiling ( #2459 )
...
* Add autoShape() speed profiling
* Update common.py
* Create README.md
* Update hubconf.py
* cleanuip
2021-03-13 19:50:34 -08:00
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>
2021-03-06 12:02:10 -08:00
a3ecf0fd64
Anchor override ( #2350 )
2021-03-02 23:08:21 -08:00
fab5085674
EMA bug fix 2 ( #2330 )
...
* EMA bug fix 2
* update
2021-03-01 17:13:34 -08:00
fd96810518
remove TTA 1 pixel offset ( #2325 )
2021-02-28 21:14:08 -08:00
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>
2021-02-26 15:07:40 -08:00
95aefea493
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>
2021-02-21 21:50:44 -08:00
c09964c27c
Update inference default to multi_label=False ( #2252 )
...
* Update inference default to multi_label=False
* bug fix
* Update plots.py
* Update plots.py
2021-02-19 15:39:09 -08:00
5f42643a53
Unified hub and detect.py box and labels plotting ( #2243 )
2021-02-19 12:38:05 -08:00
db28ce61ac
Improved hubconf.py CI tests ( #2251 )
2021-02-19 12:35:38 -08:00
9d87307784
YOLOv5 Hub URL inference bug fix ( #2250 )
...
* Update common.py
* Update common.py
* Update common.py
2021-02-19 11:22:42 -08:00
f8464b4f66
Update yolo.py channel array ( #2223 )
2021-02-15 21:21:53 -08:00
3ff783c18f
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>
2021-02-15 10:49:22 -08:00
3e560e2fae
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>
2021-02-12 15:37:51 -08:00
404749a33c
PyTorch Hub results.save('path/to/dir') ( #2179 )
2021-02-10 16:10:43 -08:00
9646ca438a
Update plot_study() ( #2112 )
2021-02-01 13:51:11 -08:00
6e6f77be47
Add YOLOv5-P6 models ( #2083 )
2021-01-29 11:57:29 -08:00
6bfa9c2422
GhostConv update ( #2082 )
2021-01-29 11:25:01 -08:00
08d3119e09
Add histogram equalization fcn ( #2049 )
2021-01-26 17:30:42 -08:00
2fc4760257
Update autoshape .print() and .save() ( #2022 )
2021-01-22 16:38:06 -08:00
aac33f87ad
Update inference multiple-counting ( #2019 )
...
* Update inference multiple-counting
* update github check
2021-01-22 15:39:08 -08:00
4501169547
Update yolo.py with yaml.SafeLoader ( #1970 )
2021-01-18 10:47:00 -08:00
03ebe6ea14
Add nn.SiLU inplace in attempt_load() ( #1940 )
...
* sleep 3 sec to load data .
* Update train.py
* Add nn.SiLU inplace in attempt_load()
Co-authored-by: wangliang <wangliang@codingapi.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2021-01-15 09:58:41 -08:00
1d1c0567a4
PyTorch Hub results.render() ( #1897 )
2021-01-10 20:06:11 -08:00
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
2021-01-04 19:54:09 -08:00
0b6266f5e0
Update yolov3-tiny.yaml ( #1823 )
2021-01-02 13:01:05 -08:00
14b0abe2d0
autoShape() default for PyTorch Hub models ( #1692 )
...
* Add autoshape parameter
* Remove autoshape call in ReadMe
* Update hubconf.py
* file/URI inputs and autoshape check passthrough
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
2020-12-26 19:58:26 -08:00
9922c1183f
leaf Variable inplace bug fix ( #1759 )
2020-12-22 17:27:40 -08:00
394d1c89f3
Input channel yaml['ch'] addition ( #1741 )
2020-12-19 10:54:01 -08:00
6bd5e8bca7
nn.SiLU() export support ( #1713 )
2020-12-16 17:55:57 -08:00
799724108f
Update C3 module ( #1705 )
2020-12-15 22:13:08 -08:00
fa8f1fb0e9
Simplify autoshape() post-process ( #1653 )
...
* Simplify autoshape() post-process
* cleanup
* cleanup
2020-12-09 07:44:06 -08:00
791dadb51c
Pycocotools best.pt after COCO train ( #1616 )
...
* Pycocotools best.pt after COCO train
* cleanup
2020-12-06 14:58:33 +01:00
d929bb656c
Implement default class names ( #1609 )
2020-12-06 12:41:37 +01:00
ba48f867ea
Add bias to Classify() ( #1601 )
2020-12-04 15:06:33 +01:00
199c9c7874
Detection() device bug fix ( #1455 )
2020-11-19 13:45:36 +01:00
Glenn Jocher
Ding Yiwei
Ayush Chaurasia
Jan Hajek
oleg
Aditya Lohia
Yann Defretin
VdLMV
Daniel Khromov
Abhiram V
lorne
NanoCode012