Which pre-trained segmentation algorithm is used to get semantic and instance maps?

NVIDIA / vid2vid

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

Other

8.57k stars 1.2k forks source link

Which pre-trained segmentation algorithm is used to get semantic and instance maps? #87

Open RyanY1994 opened 5 years ago

RyanY1994 commented 5 years ago

Which pre-trained segmentation algorithm is used to get semantic and instance maps? Btw, as you mentioned in another paper (pix2pixHD), should the instance maps be their boundary map format? However, the instance maps you provided in 'train_inst' folder are just instance maps with cars labeled. Thank you!

nivedyaammu commented 5 years ago

Please guide me in generating instance masks. Or please provide the model you have used for the generation of instance maps.

JamesChenChina commented 5 years ago

https://github.com/NVIDIA/vid2vid/issues/61