Constructs YOLOv5 model with TorchVision MobileNetV3 backbone

[zhiqwang]

We use TorchVision layout to construct a high resolution YOLOv5 model with TorchVision pre-trained MobileNetV3-Small FPN backbone.

import torch
from yolort.models.yolo_lite import yolov5_mobilenet_v3_small_fpn

model = yolov5_mobilenet_v3_small_fpn()
model = model.eval()

images = torch.rand(4, 3, 640, 640)
out = model(images)

[codecov]

Codecov Report

Merging #342 (d67cc33) into main (de11966) will not change coverage.
The diff coverage is n/a.

@@           Coverage Diff           @@
##             main     #342   +/-   ##
=======================================
  Coverage   95.46%   95.46%           
=======================================
  Files          11       11           
  Lines         771      771           
=======================================
  Hits          736      736           
  Misses         35       35           

Flag	Coverage Δ
unittests	95.46% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out 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 de11966...d67cc33. Read the comment docs.