feat: add RandomCrop module in transforms

[charlesmindee]

This PR adds RandomCrop in transforms/base.py, and updates the detection dataset with a geometric_transforms args to compose both RandomCrop and RandomRotate.

Any feedback is welcome!

NB: cropping should be performed BEFORE rotation, because it is lighter that way (less information to deal with), and also because the rotation transformation converts boxes to rotated boxes whereas cropping is performed with straight bounding boxes.

[fg-mindee]

Thanks for the PR!

I think we should keep this PR about the sole implementation of the cropping augmentation (and handle the integration of img+target transforms in the datasets in another PR), cf my comments :)

[fg-mindee]

Thanks for the edits! Only a few comments left

[codecov]

Codecov Report

Merging #448 (d84e655) into main (d2fef17) will decrease coverage by 0.00%.
The diff coverage is 95.23%.

@@            Coverage Diff             @@
##             main     #448      +/-   ##
==========================================
- Coverage   95.84%   95.83%   -0.01%     
==========================================
  Files          96       96              
  Lines        3997     4014      +17     
==========================================
+ Hits         3831     3847      +16     
- Misses        166      167       +1     

Flag	Coverage Δ
unittests	95.83% <95.23%> (-0.01%)	⬇️

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

Impacted Files	Coverage Δ
doctr/transforms/modules/base.py	91.22% <95.23%> (+1.22%)	⬆️

---

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 d2fef17...d84e655. Read the comment docs.

[fg-mindee]

Thanks ! Looks good to me, could you add an entry in the documentation please? 🙏

[fg-mindee]

Cheers!