Wenxi Ma

[Feature Request] Add support for pooling blocks

4

e.g. The implementation in MinkowskiEngine: [https://nvidia.github.io/MinkowskiEngine/pooling.html#minkowskimaxpooling](url). I only found global_max_pool()

### Describe your suggested feature Since the upstream repository Tachiyomi has been deleted, do we need to switch to another upstream? e.g. mihon. ### Other details _No response_ ### Acknowledgements...

When I'm doing a generative transpose convolution on a tensor. An error occured: AssertionError: spatial range must be specified in generative mode This seems to because I didn't specify the...

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior Does TorchSparse support generate `Conv3D()` results on another set of coordinates?...

As mentioned in #309, there is no implementation for generating Conv3D results on another set of coordinates. It would be very helpful if implemented.

尤太->犹太

resolution unmatch

1

Hi, I'm trying to run this model on my own Mip-NeRF dataset (which is originally COLMAP format and be transformed to MVS format by [https://github.com/YoYo000/MVSNet#mvsnet-input-from-sfm-output](url) The input image has an...