BYOL implementation

[annikabrundyn]

Closes #114

[pep8speaks]

Hello @annikabrundyn! Thanks for updating this PR.

There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻

Comment last updated at 2020-08-05 16:13:07 UTC

[annikabrundyn]

FYI @ananyahjha93 @vladisai - still finishing this up :)

[codecov]

Codecov Report

Merging #144 into master will increase coverage by 0.19%.
The diff coverage is 98.05%.

@@            Coverage Diff             @@
##           master     #144      +/-   ##
==========================================
+ Coverage   91.11%   91.30%   +0.19%     
==========================================
  Files          82       85       +3     
  Lines        4039     4142     +103     
==========================================
+ Hits         3680     3782     +102     
- Misses        359      360       +1     

Flag	Coverage Δ
#unittests	91.30% <98.05%> (+0.19%)	⬆️

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

Impacted Files	Coverage Δ
...l_bolts/models/self_supervised/byol/byol_module.py	96.42% <96.42%> (ø)
pl_bolts/callbacks/self_supervised.py	100.00% <100.00%> (ø)
pl_bolts/models/self_supervised/__init__.py	100.00% <100.00%> (ø)
pl_bolts/models/self_supervised/byol/models.py	100.00% <100.00%> (ø)
pl_bolts/optimizers/layer_adaptive_scaling.py	94.00% <0.00%> (+2.00%)	⬆️

---

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 f409d5e...352e140. Read the comment docs.