MMNet icon indicating copy to clipboard operation
MMNet copied to clipboard

Code for Towards Real-Time Automatic Portrait Matting on Mobile Devices

Results 11 MMNet issues
Sort by recently updated
recently updated
newest added

Hello How are you? Thanks for contributing this project. Could u provide the inference script for an image? Thanks

Hi, Thank you so much for such a wonderful work. Can this model be used for getting real-time alpha mattes for images other than portraits as well? Like, Would the...

Is there an option which can continue-train if I have to break and I want to train continuely from last training coondition?

When I train, the log will output in the terminal, but I can't find a log_file in the project path? Is there a log_file for reviewing?

I found it train on CPU

Why change # Before: [SpaceToBatchND] -> [DepthwiseConv2dNative] -> [BatchToSpaceND] -> [normalize] -> [activate] to # After : [SpaceToBatchND] -> [DepthwiseConv2dNative] -> [normalize] -> [activate] -> [BatchToSpaceND]

This "--convert_to_pb" in evaluator.py but no relevant codes to do it?

@shurain 안녕하세요. 좋은 소스를 공개해주셔서 감사합니다. 이모델을 트레이닝 하려고 하는데, 데이터셋의 구성을 어떻게 해야 하는건가요? 제안하신 디렉토리 구조는 이해가 됩니다. dataset_directory |___ train | |__ mask | |__ image |...