(from https://github.com/xuebinqin/DIS)
Ailia input shape(1, 3, Y, X) where X and Y are multiples of 64 Range:[0, 1]
Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.
For the sample image,
$ python3 dis_seg.py
If you want to specify the input image, put the image path after the --input option.
You can use --savepath option to change the name of the output file to save.
$ python3 dis_seg.py --input IMAGE_PATH --savepath SAVE_IMAGE_PATH
By adding the --video option, you can input the video.
If you pass 0 as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.
$ python3 dis_seg.py --video VIDEO_PATH
The default setting is to use the optimized model and weights, but you can also switch to the normal model by using the --normal option.
Highly Accurate Dichotomous Image Segmentation
PyTorch
ONNX opset = 12