facebookresearch / Mask2Former

Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
MIT License
2.59k stars 388 forks source link

Running training using my current segmentation masks without making and saving the segmentation masks #155

Open cjfghddl0206 opened 2 years ago

cjfghddl0206 commented 2 years ago

It is divided into training and test files, so only the mask file and the image file are in jpg format, and the other files are not. So, I want to train without having to convert it to a mask file, but I wonder if it can work without using the Bitmasks part that saves the segmentation mask as a single image.

yufeng89 commented 1 year ago

I met same problem,have you solved it?