YOLOv5 segmentation now is possible!

[hdnh2006]

In this PR you will be able to use YOLOv5 segmentation from Ultralytics to create masks and accelerate the process in labeling data.

All the segmentation models can be downloaded from here: https://github.com/hdnh2006/anylabeling-assets/releases/tag/v0.0.0

They have been exported with --opset 12 as option as following: python export.py --weights yolov5x-seg.pt --include onnx --opset 12

An important change has been done in the blob preprocessing of all yolo models, since the image is already in BGR format, so swapRB=False has been set in order to avoid changes in the channels.

Again, if there is any change you need, please let me know.

[vietanhdev]

There are some differences between your YOLOv5 segmentation result with the result from this repo (using the same model).

For YOLOv5n Segmentation

• Result from: https://github.com/Hyuto/yolov5-seg-python

• Result from your implementation:

Note: Missing chairs and not good segmentation result in the man's leg.

For YOLOv5x Segmentation

• Result from: https://github.com/Hyuto/yolov5-seg-python

• Result from your implementation:

Could you please check the implementation for the reason? Thank you!

[hdnh2006]

Thanks @vietanhdev,

Please, could you share the image you are using? so both, can work on the same source.

[vietanhdev]

Please check this image. photo-1595950009887-e9842bcbc1ae.png.zip