DeepLab is a state-of-art deep learning model for semantic image segmentation, where the goal is to assign semantic labels (e.g., person, dog, cat and so on) to every pixel in the input image. Here is mobile version running on Android devices.
Here is demo screen recording.
Download the frozen graph mobilenetv2_coco_voc_trainaug from Deeplab github and put to assets folder.
Crashes with the exception no OpKernel was registered to support Op 'Slice' with these attrs
Forked from https://github.com/dailystudio/ml/tree/master/deeplab