torchmcubes

torchmcubes copied to clipboard

torch should be a requirement

2

One cannot install torchmcubes without torch. Please add it to the requirements or instructions: pip install torch

truedat101

I just cant install the library

8

Command: ``` pip install git+https://github.com/tatsy/torchmcubes.git ``` Error: ``` Collecting git+https://github.com/tatsy/torchmcubes.git Cloning https://github.com/tatsy/torchmcubes.git to /tmp/pip-req-build-yl8cxb4s Running command git clone --filter=blob:none --quiet https://github.com/tatsy/torchmcubes.git /tmp/pip-req-build-yl8cxb4s Resolved https://github.com/tatsy/torchmcubes.git to commit 3aef8afa5f21b113afc4f4ea148baee850cbd472 Preparing metadata (setup.py)...

math-sasso

I'm trying to install torchmcubes but I just can't get it to install this is the log of what I'm getting ``` Collecting git+https://github.com/tatsy/torchmcubes.git Cloning https://github.com/tatsy/torchmcubes.git to c:\users\v\appdata\local\temp\pip-req-build-02pr5nlq Running command...

VeeVal

Dear authors, Thanks for this excellent repo, I have one small concern, that what is the difference between this repo and the marching cube algorithm in pytorch3d: https://github.com/facebookresearch/pytorch3d/issues/532

Puzzled-Hui

Fix the input numel issue

2

Fix the "numel needs to be smaller than int32_t max; otherwise, please use packed_accessor64" issue. ``` verts, faces = self.mc_func(level.to(get_rank()), threshold) File "/usr/local/lib/python3.10/dist-packages/torchmcubes/__init__.py", line 12, in marching_cubes return mc.mcubes_cuda(vol, thresh)...

yuanxion

Scale and order of verts output (how to transform to input frame)?

2

My data volume consists of xyz input ``` n1, n2, n3 = 80, 80, 50 xv, yv, zv = torch.meshgrid( [torch.linspace(-0.2, 0.2, n1), torch.linspace(-0.2, 0.2, n2), torch.linspace(0, 0.5, n3)]) ```...

LemonPi

Thanks for writting this up. I tried the code and got very good results with the CPU implementation. However, there's seems to be an issue with the vertix pruning in...

dkimanius

nvcc fatal : Unsupported gpu architecture 'compute_' [With Solution]

2

Hi, when I use `pip install git+https://github.com/tatsy/torchmcubes.git` to install, it will cause: I am using Python 3.12.2 and CUDA 12.2. ```bash pip install git+https://github.com/tatsy/torchmcubes.git Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple Collecting git+https://github.com/tatsy/torchmcubes.git...

aruiplex

Failed to build torchmcubes

4

Requirement already satisfied: numpy in e:\ai\triposr\python_embeded\lib\site-packages (from torchmcubes==0.1.0) (1.26.4) Requirement already satisfied: torch in e:\ai\triposr\python_embeded\lib\site-packages (from torchmcubes==0.1.0) (2.2.1+cu118) Requirement already satisfied: filelock in e:\ai\triposr\python_embeded\lib\site-packages (from torch->torchmcubes==0.1.0) (3.12.2) Requirement already satisfied:...

liuxb99

change to make use of CMake 3.18+ inbuilt functionality to detect GPU architecture code. solves : https://github.com/tatsy/torchmcubes/issues/18 also adds note about having nvcc in path to README.md

sarangzambare