martinkersner / train-DeepLab

Train DeepLab for Semantic Image Segmentation
MIT License
172 stars 76 forks source link

Fast version of convert_from_color_segmentation #18

Closed bermanmaxim closed 7 years ago

bermanmaxim commented 7 years ago

Hi, minor improvement here, but it might be useful to other people that want to convert the VOC2012 segmentation masks to 1D images; using a vectorized numpy form saves lots of time (10-fold improvement).

martinkersner commented 7 years ago

@bermanmaxim Thanks! Your improvement is great!