Support yolov5x and yolov5x6 models

[ShiquanYu]

Support yolov5x and yolov5x6 models

from yolort.models import YOLOv5

# 'yolov5x.pt' is downloaded from https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5x.pt
ckpt_path_from_ultralytics = "yolov5x.pt"
model = YOLOv5.load_from_yolov5(ckpt_path_from_ultralytics, score_thresh=0.25)

model.eval()
img_path = "test/assets/bus.jpg"
predictions = model.predict(img_path)

[codecov]

Codecov Report

Merging #261 (0934555) into main (5dc8996) will not change coverage.
The diff coverage is n/a.

❗ Current head 0934555 differs from pull request most recent head b435234. Consider uploading reports for the commit b435234 to get more accurate results

@@           Coverage Diff           @@
##             main     #261   +/-   ##
=======================================
  Coverage   93.62%   93.62%           
=======================================
  Files          11       11           
  Lines         675      675           
=======================================
  Hits          632      632           
  Misses         43       43           

Flag	Coverage Δ
unittests	93.62% <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 5dc8996...b435234. Read the comment docs.