Update framework for the use of real/imag

[FeGeyer]

Major changes:

• Add normalization callback with two different techniques
• Update plotting routines for real/imag images
• Update use of ms-ssim
• Update evaluate_area and evaluate_ms_ssim for half images
• Add evaluate_ms_ssim for sampled images

Small changes:

• Add the model name to predictions and sampling file
• Delete unnecessary pad_unsqueeze function
• Add amp_phase keyword to sample_images
• Fix deprecation warning in sampling.py
• Add image size to test_evaluation.py routines

To-Do

• Add loading of normalization factors
• Add automatic rescaling for evaluation routines

[codecov-commenter]

Codecov Report

Base: 47.59% // Head: 47.37% // Decreases project coverage by -0.23% ⚠️

Coverage data is based on head (ef46a80) compared to base (1561e49).
Patch coverage: 36.76% of modified lines in pull request are covered.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #146      +/-   ##
==========================================
- Coverage   47.59%   47.37%   -0.23%     
==========================================
  Files          32       32              
  Lines        3494     3635     +141     
==========================================
+ Hits         1663     1722      +59     
- Misses       1831     1913      +82     

Impacted Files	Coverage Δ
radionets/dl_framework/architectures/res_exp.py	34.86% <0.00%> (+0.31%)	⬆️
radionets/evaluation/plotting.py	35.09% <0.00%> (-0.60%)	⬇️
radionets/dl_framework/callbacks.py	43.12% <19.23%> (-3.36%)	⬇️
radionets/evaluation/train_inspection.py	48.81% <31.46%> (-2.29%)	⬇️
radionets/dl_framework/model.py	54.14% <42.85%> (-0.53%)	⬇️
radionets/dl_framework/learner.py	85.29% <50.00%> (-2.21%)	⬇️
radionets/dl_training/scripts/start_training.py	57.33% <50.00%> (-0.21%)	⬇️
radionets/evaluation/utils.py	65.68% <52.00%> (-0.87%)	⬇️
radionets/dl_training/utils.py	83.15% <100.00%> (+5.38%)	⬆️
radionets/simulations/sampling.py	77.14% <100.00%> (ø)

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.