unsupervised contrastive loss

[Dante-Basile]

Reference issue

#520

Type of change

This contains the loss function and a basic ResNet50 demo demonstrating training and decreasing loss on CIFAR-10.

What does this implement/fix?

This demonstrates that the ResNet50 network can effectively optimize the loss of the unsupervised contrastive loss function. Future experiments will examine the accuracy of the trained network.

Additional information

NDD 2021

[PSSF23]

Refer to file structure in #518

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 90.09%. Comparing base (634d4d1) to head (8373149).
⚠️ Report is 112 commits behind head on staging.

Additional details and impacted files

@@           Coverage Diff            @@
##           staging     #522   +/-   ##
========================================
  Coverage    90.09%   90.09%           
========================================
  Files            7        7           
  Lines          404      404           
========================================
  Hits           364      364           
  Misses          40       40           

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[PSSF23]

@Dante-Basile You need to black format the files.

@jdey4 do you think this is an ideal way to separate supervised & unsupervised? Or should there be separate folders in benchmarks?

[PSSF23]

• Your notebooks have unnecessary outputs & empty cells. Remove them.
• Remove commented lines of code