Generelize UNet: custom # of input channels (instead of default 3)

[annikabrundyn]

No description provided.

[codecov]

Codecov Report

Merging #297 into master will decrease coverage by 6.40%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #297      +/-   ##
==========================================
- Coverage   81.85%   75.45%   -6.41%     
==========================================
  Files          98      100       +2     
  Lines        5495     6087     +592     
==========================================
+ Hits         4498     4593      +95     
- Misses        997     1494     +497     

Flag	Coverage Δ
#cpu	23.47% <0.00%> (-0.02%)	⬇️
#pytest	23.47% <0.00%> (-0.02%)	⬇️
#unittests	81.26% <100.00%> (-0.04%)	⬇️

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

Impacted Files	Coverage Δ
pl_bolts/models/vision/unet.py	98.03% <100.00%> (ø)
pl_bolts/callbacks/self_supervised.py	45.83% <0.00%> (-54.17%)	⬇️
pl_bolts/models/rl/dueling_dqn_model.py	62.50% <0.00%> (-37.50%)	⬇️
pl_bolts/models/rl/double_dqn_model.py	60.52% <0.00%> (-35.31%)	⬇️
pl_bolts/models/rl/per_dqn_model.py	56.38% <0.00%> (-30.51%)	⬇️
...l_bolts/models/rl/vanilla_policy_gradient_model.py	65.83% <0.00%> (-26.13%)	⬇️
pl_bolts/utils/semi_supervised.py	71.27% <0.00%> (-25.45%)	⬇️
pl_bolts/models/self_supervised/moco/transforms.py	74.76% <0.00%> (-25.24%)	⬇️
pl_bolts/models/rl/noisy_dqn_model.py	58.46% <0.00%> (-24.15%)	⬇️
pl_bolts/datasets/ssl_amdim_datasets.py	53.46% <0.00%> (-20.86%)	⬇️
... and 14 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 dc16e7b...39c42c0. Read the comment docs.