Custom Shufflenetv2 for extremely small and dense objects

[vuongnp]

Add new stride: 4
Total strides of the model: 4, 8, 16, 32, 64

[codecov]

Codecov Report

❌ Patch coverage is 56.31068% with 45 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.42%. Comparing base (226d8cc) to head (4e25651).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
nanodet/model/backbone/shufflenetv2_dense.py	56.00%	36 Missing and 8 partials ⚠️
nanodet/model/backbone/__init__.py	66.66%	0 Missing and 1 partial ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #528      +/-   ##
==========================================
- Coverage   74.80%   74.42%   -0.38%     
==========================================
  Files          71       72       +1     
  Lines        4695     4798     +103     
  Branches      731      753      +22     
==========================================
+ Hits         3512     3571      +59     
- Misses        986     1022      +36     
- Partials      197      205       +8     

Flag	Coverage Δ
unittests	74.42% <56.31%> (-0.38%)	⬇️

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.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[RangiLyu]

Thanks for your contribution! You can introduce the features of this model in the readme and the comments of the config to let other users know it better.