search

svip-lab / PlanarReconstruction

[CVPR'19] Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding
MIT License
363 stars 85 forks source link

change decoder #40

Closed KirillHiddleston closed 3 years ago

KirillHiddleston commented 3 years ago

Hello. How to change decoder for semantic segmentation ?

niujinshuchong commented 3 years ago

@KirillHiddleston I think you can add a head similar to here https://github.com/svip-lab/PlanarReconstruction/blob/master/models/baseline_same.py#L75 to output semantic segmentation.