tiny-cuda-nn icon indicating copy to clipboard operation
tiny-cuda-nn copied to clipboard

Lightning fast C++/CUDA neural network framework

Results 203 tiny-cuda-nn issues
Sort by recently updated
recently updated
newest added

Describe the bug Getting the following error when trying to run `pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch` Produce the following output: ``` error: subprocess-exited-with-error × python setup.py bdist_wheel did not run successfully. │...

https://github.com/sdbds/tiny-cuda-nn-for-windows/ I cost 4hours to compile it. Just leave your words of gratitude

python:3.8.16 CUDA Version: 12.0 (nerfstudio) lt@user:~/down/tiny-cuda-nn-master/bindings/torch$ python setup.py install Building PyTorch extension for tiny-cuda-nn version 1.7 Obtained compute capability 80 from PyTorch sh: 1: nvcc: not found running install running...

Hi @Tom94, As second order derivative is a common operation in 3D reconstruction (neural SDF related), there sometimes requires an Eikonal loss during training, in which a first order derivative...

I got the following error when installing `/envs/nerfstudio/lib/python3.10/site-packages/torch/utils/cpp_extension.py", line 849, in build_extensions build_ext.build_extensions(self) File "/home/tianshu/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/setuptools/_distutils/command/build_ext.py", line 467, in build_extensions self._build_extensions_serial() File "/home/tianshu/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/setuptools/_distutils/command/build_ext.py", line 493, in _build_extensions_serial self.build_extension(ext) File "/home/tianshu/miniconda3/envs/nerfstudio/lib/python3.10/site-packages/setuptools/command/build_ext.py", line...

Hello, thank you very much for sharing this work When I execute the cmake command, prompt: -- Targeting CUDA architectures: 61 CMake Warning at CMakeLists.txt:194 (message): Fully fused MLPs do...

OS: windows 10. Try to use nerfstudio, all dependecies has installed by this command: conda create --name nerfstudio -y python=3.8 conda activate nerfstudio python -m pip install --upgrade pip pip...

I'm using rtx4090, supported by cuda-toolkit version >= 11.7. In a project I have to use torch1.12(compiled by cuda

Hi, I would like to condition my decoder with FiLM modulations, but I am a bit struggling to understand what to modify in the code of modules.py. Do you have...

Thanks to the developers for making this exciting effort available! I'd like to request the inclusion of the SiLU nonlinearity, which should be a very simple modification of the existing...