-
In Sparse/models/SparseTSF.py, the kernel size of nn.Conv1d() is set to 1 + 2 * self.period_len // 2. As I try to use an odd period_len, It will raise error saying the shape of input x can not match i…
-
Hi Choy. Thanks for your great work on this project! I'm trying to calculate the second derivatives of sparse tensor operations (e.g. sparse convolution). I found that the backward operation of sparse…
-
Hi, in your PTv3 paper, a variety of positional encoding method are discussed, with CPE being chosen and implemented using SpConv.
Considering hardware constraints, storing grid positions and perfo…
-
We will release a number of new features or improvements with version 1.5 (see [Draft release notes](https://github.com/helmholtz-analytics/heat/releases) for what's been already merged, and [PRs](htt…
-
It’s tricky to do efficiently so we should have an implementation here (even though it doesn’t need a new atom). We should also speed up the sparse matrix creation in the 1D convolution.
I impleme…
-
Hello, I'm trying to use the generalized convolution of sparse tensors and want to ask you guys how to use it, cause the issues that I've looked seems to support generalized convolution as in Minkowsk…
-
Hi, I'm trying to install [tf3d](https://github.com/google-research/google-research/tree/master/tf3d) but encounter a problem of step 1 [Preparing and Compiling the Sparse Conv Op](https://github.com/…
-
Dear Devs,
thank you for this library. I am currently writing my model using it, but I am a bit confused about the usage. I am working with sparse matrices but I find myself struggling with which typ…
-
https://github.com/jingyue202205/SE-SSD-AI-TRT
3D submanifold convolution and 3D sparse convolution TensorRT plugins
-
I recently had the opportunity to read your paper "SpENCNN: Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted Neural Network Inference". In the paper you mentioned that for convol…