anime-segmentation

Anime Segmentation

Input

(Image from https://datasets-server.huggingface.co/assets/skytnt/anime-segmentation/--/imgs-masks/train/51/image/image.jpg)

Output

Usage

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 anime-segmentation.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 anime-segmentation.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 anime-segmentation.py --video VIDEO_PATH

Reference

• Anime Segmentation
• Hugging Face - skytnt/anime-segmentation

Framework

PyTorch

Model Format

ONNX opset = 11

Netron

isnetis.onnx.prototxt