Pywick

Another great improvement to the framework - docker! You can now run the 17flowers demo right out of the box!

- Grab our docker image at docker hub: `docker pull achaiah/pywick:latest.` Pytorch 1.8 and cuda dependencies are pre-installed.
- Run 17flowers demo with: `docker run --rm -it --ipc=host -v your_local_out_dir:/jobs/17flowers --init -e demo=true achaiah/pywick:latest`
- Or run the container in standalone mode so you can use your own data (don't forget to map your local dir to container):


docker run --rm -it \
--ipc=host \
-v <your_local_data_dir>:<container_data_dir> \
-v <your_local_out_dir>:<container_out_dir> \
--init \
achaiah/pywick:latest

Huge release with new functionality and models!

- Complete configuration support via YAML files. Run your training without writing a single line of code!
- Classification training example with a fully functional YAML config.
- 700+ classification models.
- Improvements to code-base via deepsource.
- New Loss functions.
- New Segmentation models.

Small corrections for pypi and README. No functional changes.

Added ~50 new models (including many variants of efficientnet, mixnet, mnasnet etc).
SoTA activation function (Mish)
New otimizers (Ralamb, Ranger, Lookahead)

Major changes (see readme for details):
- Added many new segmentation models (most are pretrained)
- Added new optimizers
- Added new loss functions
- Improved model loading logic
- Various bug fixes

We've gone to great lengths to create good readable documentation for Pywick. You can [peruse it here](https://pywick.readthedocs.io/en/latest).