Improved penalty calculation and added ImageNet-specific VGG

[Geeks-Sid]

Fixes #ISSUE_NUMBER

Proposed Changes

Checklist

• I have read the CONTRIBUTING guide
• My PR is based from the current GaNDLF master
• Non-breaking change (would not break existing functionality): please provide as many details as possible for any breaking change
• Function/class source code documentation added/updated
• Code has been blacked for style consistency
• If applicable, version information has been updated in GANDLF/version.py
• If adding a git submodule, add to list of exceptions for black styling in pyproject.toml file
• Usage documentation has been updated, if appropriate
• History has been updated, if appropriate
• Tests added or modified to cover the changes; if coverage is reduced, please give explanation
• If customized dependency installation is required (i.e., a separate pip install step is needed for PR to be functional), please ensure it is reflected in all the files that control the CI, namely: python-test.yml, and all docker files [1,2,3,4]

[codecov]

Codecov Report

Merging #365 (a047ef8) into master (0301b91) will decrease coverage by 0.02%.
The diff coverage is 88.46%.

@@            Coverage Diff             @@
##           master     #365      +/-   ##
==========================================
- Coverage   91.57%   91.54%   -0.03%     
==========================================
  Files          92       93       +1     
  Lines        5316     5394      +78     
==========================================
+ Hits         4868     4938      +70     
- Misses        448      456       +8     

Flag	Coverage Δ
unittests	91.54% <88.46%> (-0.03%)	⬇️

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

Impacted Files	Coverage Δ
GANDLF/data/ImagesFromDataFrame.py	88.88% <ø> (+0.81%)	⬆️
GANDLF/utils/__init__.py	100.00% <ø> (ø)
GANDLF/utils/parameter_processing.py	91.48% <ø> (ø)
GANDLF/models/imagenet.py	70.00% <70.00%> (ø)
GANDLF/compute/training_loop.py	83.88% <100.00%> (+0.90%)	⬆️
GANDLF/losses/regression.py	92.04% <100.00%> (-0.09%)	⬇️
GANDLF/models/__init__.py	100.00% <100.00%> (ø)
GANDLF/utils/tensor.py	81.37% <100.00%> (+1.68%)	⬆️
testing/test_full.py	98.26% <100.00%> (+0.03%)	⬆️
... and 2 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 0301b91...a047ef8. Read the comment docs.

[Geeks-Sid]

@sarthakpati Can you check why the CI is failing, i think it is an issue with the data in itself where one of the columns is named wrong.

[sarthakpati]

LGTM!

[sarthakpati]

LGTM!