torchsparse

torchsparse copied to clipboard

[Feature Request / Question] Modifications Required to run on ARM / M1

20

Since I didn't see any mention of M1 or ARM and the current build fails. I was wondering what changes may be needed to support the architecture. Short Version: ```...

The-Real-Thisas

[BUG] spnn.Conv3d cuda and cpu the inference results are not comparable

1

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior 我正在尝试移植 spnn.Conv3d，但是发现cuda 版本和cpu 版本的推理结果是有差异。 spnn.Conv3d的参数如下： self.conv3d=spnn.Conv3d(4, 32, 3,1) ### Expected Behavior...

jacker-whh

[Installation] build from source succeed, while encounter errors in running.

4

### Is there an existing issue for this? - [X] I have searched the existing issues ### Have you followed all the steps in the FAQ? - [X] I have...

zouyuanpeng

[BUG] AttributeError: 'SparseTensor' object has no attribute 'is_cuda' for SYNCBATCHNORM

6

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior I am running the SPVCNN model building using torchsparse. Using torchpack...

sandeepnmenon

Reproducing results in the paper

4

Hello, How can we reproduce the results in the TorchSparse paper at Figure 11? Do you provide the implementation of MinkUNet and CenterPoint that utilizes TorchSparse? Also, when I look...

ahmedius2

[BUG] <RuntimeError: Tensors of type TensorImpl do not have sizes>

2

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior ``` Traceback (most recent call last): File "main.py", line 353, in...

linzhenyuyuchen

In file backend/hash/hash_cuda.cu, the following variable appears unused for the hash calculation: `extern __shared__ int kernel_offset_local[]; ` Am I missing something or is this variable supposed to be used in...

ahmedius2

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior When we test the functions of hash, we meet the error...

zjp-shadow

In this PR we implement optimization techniques introduced in our MLSys paper "TorchSparse: Efficient Point Cloud Inference Engine". These include adaptive matrix multiplication grouping and vectorized, quantized and fused locality-aware...

Xiuyu-Li

[BUG] Voxelization results differ significantly between the CPU and CUDA implementation

1

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior Using `spvoxelize` with CUDA tensors results in voxel features greater than...

alexanderswerdlow