-
Hi, i've noticed a great speedup when i used lookup based convolutions for training my own network, however the speedup on the inference is quite marginal so i have been wondering if i need to change …
-
Is the sparse convolution you designed not open-source, and is it necessary to install sparseconv in readme.md?
-
hi,
in this project the onnx file generated from spconv has a static input size of 5*1, while the generated trt engine from the onnx file shoud have an input size of voxelNumber*5 which is dynamic , …
-
Hello,
i'm trying to implement sparse convolution layer in c++ with tensorrt, but facing a great efficiency problem. The core step of sparse conv:
```cpp
auto conv_res = ConvGemmOps::implicit_gemm…
-
**Amazing！** I have been using spconv1 before, but now I have switched to **spconv2.1**. It is amazing. It used to take 3 hours to train one epoch, but now it only takes 1.5 hours. And the GPU memory …
-
Grouped convolution is supported well in `pytorch`'s convolution layers / ops. If possible, it would a great to add that ability to `torchsparse`.
-
I found out by given the same set of inputs always receiving slightly different outputs. The diff is roughly about 10^-5. This is awkward. Is there any randomness involved in the implementation of 3DC…
-
Hi,
I found your work on involution very interesting, and it relates to other ideas I am working on like deformable convolutions. So I tried reimplementing your idea for sparse point clouds using …
-
Is there any theoretical explanation why **Asymmetrical block** better than a (sparse) 3D Convolution kernel? Normally 3D CNN should have more parameters and bigger receptive field
-
Hi @HRLTY and @afathi3, could you please also provide wheel for python 3.8 for sparse convolution op? Python 3.8 is the default for Ubuntu 20.04 LTS.
Regards,