feat: add mobilenet weights for character classification (TF)

[charlesmindee]

This PR adds weights for both small and large mobilenet v3 versions trained on 32 x 32 character classification on our french vocab.
Any feedback is welcome!

[codecov]

Codecov Report

Merging #421 (557eba9) into main (94e984c) will increase coverage by 0.02%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##             main     #421      +/-   ##
==========================================
+ Coverage   95.80%   95.83%   +0.02%     
==========================================
  Files          96       96              
  Lines        3937     3939       +2     
==========================================
+ Hits         3772     3775       +3     
+ Misses        165      164       -1     

Flag	Coverage Δ
unittests	95.83% <100.00%> (+0.02%)	⬆️

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

Impacted Files	Coverage Δ
doctr/models/backbones/mobilenet/tensorflow.py	97.50% <100.00%> (+0.06%)	⬆️
...dels/detection/differentiable_binarization/base.py	91.97% <0.00%> (+0.61%)	⬆️

---

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 94e984c...557eba9. Read the comment docs.

[fg-mindee]

Thanks for the PR!