clean up gan and vae

[williamFalcon]

No description provided.

[codecov]

Codecov Report

Merging #153 into master will decrease coverage by 0.04%.
The diff coverage is 92.42%.

@@            Coverage Diff             @@
##           master     #153      +/-   ##
==========================================
- Coverage   91.99%   91.94%   -0.05%     
==========================================
  Files          83       84       +1     
  Lines        3973     3974       +1     
==========================================
- Hits         3655     3654       -1     
- Misses        318      320       +2     

Flag	Coverage Δ
#unittests	91.94% <92.42%> (-0.05%)	⬇️

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

Impacted Files	Coverage Δ
pl_bolts/callbacks/vision/confused_logit.py	100.00% <ø> (ø)
pl_bolts/callbacks/self_supervised.py	72.72% <20.00%> (-27.28%)	⬇️
pl_bolts/callbacks/variational.py	97.29% <92.30%> (-2.71%)	⬇️
pl_bolts/callbacks/vision/image_generation.py	100.00% <100.00%> (ø)
pl_bolts/datamodules/__init__.py	100.00% <100.00%> (ø)
.../models/autoencoders/basic_vae/basic_vae_module.py	92.50% <100.00%> (+0.60%)	⬆️
...l_bolts/models/self_supervised/byol/byol_module.py	96.72% <100.00%> (+0.05%)	⬆️
pl_bolts/models/self_supervised/cpc/cpc_module.py	81.96% <100.00%> (+1.14%)	⬆️
pl_bolts/utils/shaping.py	100.00% <100.00%> (ø)
... and 3 more

---

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 5f5d4c5...03b9230. Read the comment docs.