Update training script

[MateoLostanlen]

The purpose of this PR is to update the training script and to propose a collab training to make it accessible to everyone.

Please let me now in this PR if you have comment on the collab too : (https://colab.research.google.com/gist/MateoLostanlen/1300692a2ab41418276b455f4eeab64c/train-wildfire.ipynb)

[codecov]

Codecov Report

Merging #101 (c9598d6) into master (8366787) will increase coverage by 0.16%.
The diff coverage is 96.00%.

@@            Coverage Diff             @@
##           master     #101      +/-   ##
==========================================
+ Coverage   91.75%   91.92%   +0.16%     
==========================================
  Files          16       17       +1     
  Lines         631      656      +25     
==========================================
+ Hits          579      603      +24     
- Misses         52       53       +1     

Flag	Coverage Δ
unittests	91.92% <96.00%> (+0.16%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
pyrovision/models/rexnet.py	95.83% <95.83%> (ø)
pyrovision/models/__init__.py	100.00% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 8366787...657f54a. Read the comment docs.

[frgfm]

Thanks for the PR! I left a few comments, let me know what you think

[MateoLostanlen]

Done :)

[frgfm]

Thanks for the PR! Also I'm wondering, but here we modified the training script for Wildfire. If this is gonna remain our video dataset, we need to find another name to specify that it's image classification 🤷‍♂️