Weak lensing: data aug + recent DC2 results with baselines

[timwhite0]

Recent results on DC2:

BLISS:
test loss: -10.49
shear 1 test MSE: 5.3e-05
shear 2 test MSE: 5.4e-05
convergence test MSE: 6.1e-05

Baseline estimator based on true ellipticities:
shear 1 test MSE: 4.9e-05 
shear 2 test MSE: 5.1e-05

Predicting zero in every tile:
shear 1 test MSE: 6.7e-05
shear 2 test MSE: 6.4e-05

See notebooks/dc2/evaluate_encoder.ipynb in our case study for corresponding shear/convergence maps and scatterplots. Our previous results (#1074) should be disregarded because they were affected by #1075 and #1076.

Updates in this PR:

• Implemented two data augmentation transforms: flips and 90 degree rotations. The effects of these transforms on shear are documented in notebooks/weak_lensing_sims/data_augmentation.ipynb.
• Added the average ellipticity baseline estimator to lensing_metrics.
• Added ra/dec to the tile catalog.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 76.16%. Comparing base (4694457) to head (720973c).
Report is 1 commits behind head on master.

Additional details and impacted files

@@           Coverage Diff           @@
##           master    #1077   +/-   ##
=======================================
  Coverage   76.16%   76.16%           
=======================================
  Files          22       22           
  Lines        3092     3092           
=======================================
  Hits         2355     2355           
  Misses        737      737           

Flag	Coverage Δ
unittests	76.16% <ø> (ø)

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

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

[jeff-regier]

Looks good