-
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…
-
Hi, I'm interested in this work. But I don’t know what is the use of generate_indices for spa_mask.
-
Hi!
This work is pretty interesting, but I think there should are more results like in "Demystifying Local Vision Transformer: Sparse Connectivity, Weight Sharing, and Dynamic Weight" as they replace…
-
Hi @thomasverelst
Congrats, nice work! I have two questions out of curiosity:
1) Forward pass: Why did you choose to sample from the Bernoulli distribution instead of the Gumbel-softmax? To my …
-
Dear authors,
Thanks for open-source the great work!
I was able to install the dependencies, especially the fvdb following discussion in [issue #2](https://github.com/nv-tlabs/XCube/issues/2).…
-
Our experience with blasé is that sparse tensors offer large speedups, *so long as the pixel coordinates are fixed*.
This fixed pixel coordinate provision make a nearly circular inference: we need …
gully updated
11 months ago
-
Hi,
Thanks for your work.
What's main difference between VOLO and DynamicConv?
Though `Convolution` is not explicitly used,
**Convolution is equivalent with Unfold + Matrix Multiplication +…
-
Hi,
I am confused with the Adjacency Matrix in your `adj_mat.npy`. It doesn't seem to be an adjacency matrix.
Best
-
**Describe the bug**
It seems like any MinkowskiConvolution with stride > 1 produces non-deterministic features when executed on the GPU and no shared coordinate manager is used.
Running on the CP…
-
I have train alexnet-s model in cifar10 for 100 epochs:
**### dense model performance**:
**accuracy**: 8322/10000 (83.220%)
**conv layers sparsity:**
layer features.0.weight sparsity: 0.002…