Apply Transformer to YOLO

[zhiqwang]

The model structure and trained checkpoint is copy-paste from ultralytics/yolov5#2333 .

[codecov]

Codecov Report

Merging #75 (ab8bafe) into master (76f5a5d) will increase coverage by 1.44%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master      #75      +/-   ##
==========================================
+ Coverage   80.35%   81.79%   +1.44%     
==========================================
  Files           8        8              
  Lines         682      736      +54     
==========================================
+ Hits          548      602      +54     
  Misses        134      134              

Flag	Coverage Δ
unittests	81.79% <100.00%> (+1.44%)	⬆️

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

Impacted Files	Coverage Δ
test/test_models.py	94.47% <100.00%> (+1.32%)	⬆️
test/test_onnx.py	87.77% <100.00%> (+1.19%)	⬆️
test/test_torchscript.py	98.00% <100.00%> (+0.56%)	⬆️

---

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 76f5a5d...ab8bafe. Read the comment docs.