bb0aed1ba6
Created using Colaboratory
3 anni fa
2da4e7acf7
Merge PIL and OpenCV in `plot_one_box(use_pil=False)` ( #4416 )
* Merge PIL and OpenCV box plotting functions
* Add ASCII check to plot_one_box
* Cleanup
* Cleanup2
3 anni fa
63e09fdc48
Remove `encoding='ascii'` ( #4413 )
* Remove `encoding='ascii'`
* Reinstate `encoding='ascii'` in emojis()
3 anni fa
4e8c81a368
Add `yolov5s-ghost.yaml` ( #4412 )
* Add yolov5s-ghost.yaml
* Finish C3Ghost
* Add C3Ghost to list
* Add C3Ghost to number of repeats if statement
* Fixes
* Cleanup
3 anni fa
e086347377
Update plots.py ( #4407 )
3 anni fa
d9f23ed6d6
No cache option for reading datasets ( #4376 )
* no cache option
* no cache option
* bit change
* changed to 0,1 instead of True False
* Update train.py
* Update datasets.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
57c342a6a5
Simplify ONNX inference command ( #4405 )
3 anni fa
3e7c59ad3b
Fix rename `utils.google_utils` to `utils.downloads` ( #4393 )
3 anni fa
a4e4553040
W&B: Fix for 4360 ( #4388 )
* Improve docstrings and run names
* default wandb login prompt with timeout
* return key
* Update api_key check logic
* Properly support zipped dataset feature
* update docstring
* Revert tuorial change
* extend changes to log_dataset
* add run name
* bug fix
* bug fix
* Update comment
* fix import check
* remove unused import
* Hardcore .yaml file extension
* reduce code
* Reformat using pycharm
* Remove redundant try catch
* More refactoring and bug fixes
* retry
* Reformat using pycharm
* respect LOGGERS include list
* Fix
* fix
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
75d323dd8b
W&B: Add advanced features tutorial ( #4384 )
* Improve docstrings and run names
* default wandb login prompt with timeout
* return key
* Update api_key check logic
* Properly support zipped dataset feature
* update docstring
* Revert tuorial change
* extend changes to log_dataset
* add run name
* bug fix
* bug fix
* Update comment
* fix import check
* remove unused import
* Hardcore .yaml file extension
* reduce code
* Reformat using pycharm
* Remove redundant try catch
* More refactoring and bug fixes
* retry
* Reformat using pycharm
* respect LOGGERS include list
* Initial readme update
* Update README.md
* Update README.md
* Update README.md
* Update README.md
* Update README.md
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
11e4aebfef
Update README.md ( #4387 )
3 anni fa
b27f69f108
Created using Colaboratory
3 anni fa
e7fc27406a
Fix module count in parse_model ( #4379 )
Co-authored-by: yangyuantao <yangyuantao@transai.cn>
3 anni fa
ce7deec440
`int(mlc)` ( #4385 )
3 anni fa
e96c74b5a1
Simpler code for DWConvClass ( #4310 )
* more simpler code for DWConvClass
more simpler code for DWConvClass
* remove DWConv function
* Replace DWConvClass with DWConv
3 anni fa
f409d8e54f
Update README.md ( #4309 )
remove unnecessary "`"
3 anni fa
86c7150cfd
Update newline ( #4308 )
3 anni fa
e78aeac973
Evolve in CSV format ( #4307 )
* Update evolution to CSV format
* Update
* Update
* Update
* Update
* Update
* reset args
* reset args
* reset args
* plot_results() fix
* Cleanup
* Cleanup2
3 anni fa
4103ce9ad0
Simplify callbacks ( #4289 )
3 anni fa
771ac6c53d
Fixed logging level in distributed mode ( #4284 )
Co-authored-by: fkwong <huangfuqiang@transai.cn>
3 anni fa
2d99063201
Feature `python train.py --cache disk` ( #4049 )
* Add cache-on-disk and cache-directory to cache images on disk
* Fix load_image with cache_on_disk
* Add no_cache flag for load_image
* Revert the parts('logging' and a new line) that do not need to be modified
* Add the assertion for shapes of cached images
* Add a suffix string for cached images
* Fix boundary-error of letterbox for load_mosaic
* Add prefix as cache-key of cache-on-disk
* Update cache-function on disk
* Add psutil in requirements.txt
* Update train.py
* Cleanup1
* Cleanup2
* Skip existing npy
* Include re-space
* Export return character fix
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
621caea53c
W&B: Fix sweep bug ( #4276 )
* Improve docstrings and run names
* default wandb login prompt with timeout
* return key
* Update api_key check logic
* Properly support zipped dataset feature
* update docstring
* Revert tuorial change
* extend changes to log_dataset
* add run name
* bug fix
* bug fix
* Update comment
* fix import check
* remove unused import
* Hardcore .yaml file extension
* reduce code
* Reformat using pycharm
* Remove redundant try catch
* More refactoring and bug fixes
* retry
* Reformat using pycharm
* respect LOGGERS include list
* call wandblogger.log instead of wandb.log
* Fix Sweep bug
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
388016e9e3
Update 'results saved to' string ( #4275 )
3 anni fa
587c4b4b81
Add `DWConvClass()` ( #4274 )
* Add `DWConvClass()`
* Cleanup
* Cleanup2
3 anni fa
9c6732f61c
Update variables ( #4273 )
3 anni fa
306fc0119a
Update Autoshape forward header ( #4271 )
3 anni fa
53bfcbe0ae
Update AP calculation ( #4260 )
* Update AP calculation
* Cleanup
* Remove original
3 anni fa
cd540d8625
W&B: suppress warnings ( #4257 )
* Improve docstrings and run names
* default wandb login prompt with timeout
* return key
* Update api_key check logic
* Properly support zipped dataset feature
* update docstring
* Revert tuorial change
* extend changes to log_dataset
* add run name
* bug fix
* bug fix
* Update comment
* fix import check
* remove unused import
* Hardcore .yaml file extension
* reduce code
* Reformat using pycharm
* Remove redundant try catch
* More refactoring and bug fixes
* retry
* Reformat using pycharm
* respect LOGGERS include list
* call wandblogger.log instead of wandb.log
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
b74929c910
Add `train.py` and `val.py` callbacks ( #4220 )
* added callbacks
* Update callbacks.py
* Update train.py
* Update val.py
* Fix CamlCase add staticmethod
* Refactor logger into callbacks
* Cleanup
* New callback on_val_image_end()
* Add curves and results images to TensorBoard
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
d8f18834a2
Update `profile()` for CUDA Memory allocation ( #4239 )
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Update profile()
* Cleanup
3 anni fa
bceb57b910
Add `python train.py --freeze N` argument ( #4238 )
* Add freeze as an argument
I train on different platforms and sometimes I want to freeze some layers. I have to go into the code and change it and also keep track of how many layers I froze on what platform. Please add the number of layers to freeze as an argument in future versions thanks.
* Update train.py
* Update train.py
* Cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
9468657502
Update profiler ( #4236 )
3 anni fa
8d3c3ef45c
Fix weight decay comment ( #4228 )
3 anni fa
1a10b0ecd2
Created using Colaboratory
3 anni fa
083c13da45
Created using Colaboratory
3 anni fa
18f6ba77cf
Suppress torch 1.9.0 max_pool2d() warning ( #4227 )
3 anni fa
c2c958c350
Explicit `requirements.txt` location ( #4225 )
3 anni fa
7820614c40
Add `@try_except` decorator ( #4224 )
3 anni fa
b60b62e874
PyCharm reformat ( #4209 )
* PyCharm reformat
* YAML reformat
* Markdown reformat
3 anni fa
750465edae
W&B: More improvements and refactoring ( #4205 )
* Improve docstrings and run names
* default wandb login prompt with timeout
* return key
* Update api_key check logic
* Properly support zipped dataset feature
* update docstring
* Revert tuorial change
* extend changes to log_dataset
* add run name
* bug fix
* bug fix
* Update comment
* fix import check
* remove unused import
* Hardcore .yaml file extension
* reduce code
* Reformat using pycharm
* Remove redundant try catch
* More refactoring and bug fixes
* retry
* Reformat using pycharm
* respect LOGGERS include list
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
e016b15555
Update yolov5-bifpn.yaml ( #4208 )
3 anni fa
e88e8f7a98
W&B: Restructure code to support the new dataset_check() feature ( #4197 )
* Improve docstrings and run names
* default wandb login prompt with timeout
* return key
* Update api_key check logic
* Properly support zipped dataset feature
* update docstring
* Revert tuorial change
* extend changes to log_dataset
* add run name
* bug fix
* bug fix
* Update comment
* fix import check
* remove unused import
* Hardcore .yaml file extension
* reduce code
* Reformat using pycharm
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
3 anni fa
2683b18079
Update Hub Path inputs ( #4200 )
3 anni fa
1f31b7c503
Create yolov5-bifpn.yaml ( #4195 )
3 anni fa
5d66e48723
Train from `--data path/to/dataset.zip` feature ( #4185 )
* Train from `--data path/to/dataset.zip` feature
* Update dataset_stats()
* cleanup
* cleanup2
3 anni fa
3fef11706c
Update comments header ( #4184 )
3 anni fa
63a1971e31
Improve docstrings and run names ( #4174 )
3 anni fa
0ad6301c96
Update script headers ( #4163 )
* Update download script headers
* cleanup
* bug fix attempt
* bug fix attempt2
* bug fix attempt3
* cleanup
3 anni fa
f8e11483df
Update dataset headers ( #4162 )
3 anni fa
8acb5734c7
Created using Colaboratory
3 anni fa
Glenn Jocher
Ahmad Mustafa Anis
Ayush Chaurasia
Yuantao Yang
Yonghye Kwon
Sudhanshu Singh
imyhxy
junji hashimoto
Kalen Michael
IneovaAI