Add fully convolutional Focus2

[zhiqwang]

Is the Focus layer equivalent to a simple Conv layer?

Another interpretation for ultralytics/yolov5#4825 (comment)

Modified from https://github.com/airockchip/rknn_model_zoo/blob/a76fa3f6/models/vision/object_detection/yolov5-pytorch/patchs/rknpu_optimize.patch

[codecov]

Codecov Report

Base: 98.58% // Head: 98.58% // No change to project coverage 👍

Coverage data is based on head (07749be) compared to base (6b90b29).
Patch has no changes to coverable lines.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #457   +/-   ##
=======================================
  Coverage   98.58%   98.58%           
=======================================
  Files          11       11           
  Lines         778      778           
=======================================
  Hits          767      767           
  Misses         11       11           

Flag	Coverage Δ
unittests	98.58% <ø> (ø)

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

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.