* Autofix duplicate labels
PR changes duplicate label handling from report error and ignore image-label pair to report warning and autofix image-label pair.
This should fix this common issue for users and allow everyone to get started and get a model trained faster and easier than before.
* sign fix
* Cleanup
* Increment cache version
* all to any fix
* Update Objects365.yaml
Download the official Objects365 validation set and convert the labels
* Enforce 4-space indent, reformat and cleanup
* shorten list comprehension
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Add train class filter feature to datasets.py
Allows for training on a subset of total classes if `include_class` list is defined on datasets.py L448:
```python
include_class = [] # filter labels to include only these classes (optional)
```
* segments fix
* update detect.py in order to support torch script
This change assumes the torchscrip file was previously saved with `export.py`
* update `detect.py` for torchscript support
Simple update for torchscript support. Assumes the torchscript file has been generated with `export.py`
* Cleanup
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* use os.path.relpath instead of relative_to
* use os.path.relpath instead of relative_to
* Remove os.path from val.py
* Remove os.path from train.py
* Update detect.py import to os
* Update export.py import to os
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* fix different devices bug
* extend _apply() instead of to() for a general fix
* Only apply if Detect() is last layer
Co-authored-by: Jebastin Nadar <njebastin10@gmail.com>
* Indent fix
* Add comment to yolo.py
* Add comment to common.py
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
* Requirements updated
1. Requests added to requirements.txt. That might not be included in all docker base images, adding it to the requirements is safer.
2. Added a minimum version to Pandas. It's a good practice to have versions for all dependencies.
* Sort alphabetically
* Update requirements.txt
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This PR adds a new training argument `--save-period` to save training checkpoints every `x` epochs. To save training every 50 epochs for example:
```
python train.py --save-period 50 # saves epoch50.pt, epoch100.pt, epoch150.pt, ... etc.
```
This saved checkpoints in addition to existing last.pt and best.pt checkpoints and does not affect their behavior. Default value is -1, i.e. disabled.
* added callbacks
* added back callback to main
* added save_dir to callback output
* merged in upstream
* removed ghost code
* fixed parsing error for google temp links
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Temporarily reverts https://github.com/ultralytics/yolov5/pull/4978 until torch 1.10 is released, which should resolve `urllib.error.HTTPError: HTTP Error 403: rate limit exceeded` errors generated by torch hub from GitHub actions runners.
Glenn Jocher
Farley Lai
NauchtanRobotics
Ayush Chaurasia
Yoni Chechik
Andrei Ionut Damian
Jebastin Nadar
Malte Lorbach
Nan
hamid mohammadi
Egor Orel
Zhiqiang Wang
Kalen Michael