Ivan

I searched in eval.py where the mask is encoded. These two lines are the following: ` rle = pycocotools.mask.encode(np.asfortranarray(segmentation.astype(np.uint8))) rle['counts'] = rle['counts'].decode('ascii') # json.dump doesn't like bytes strings ` being...

Any update about this @liang3588 ?

Any solution? I have several .obj models with 2000 vertex and 3988 faces.

any update about this?

Hello, @HuanDinh20 Did you finally generate files *.eseg and *.seseg for your own project?. I'm really interested but i cant find any documentation related about that. Thanks in advance