search

mit-han-lab / torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.
https://torchsparse.mit.edu
MIT License
1.15k stars 131 forks source link

Does this repo support Deconv or other upsample layer? #278

Open kellenf opened 7 months ago

kellenf commented 7 months ago

Thanks for this work, but how can I use a deconv or other upsample layer? It seems not supported?

zhijian-liu commented 6 months ago

You may use the transposed sparse convolution to upsample the data: https://github.com/mit-han-lab/torchsparse/blob/master/torchsparse/backbones/modules/blocks.py#L40-L47.