Summary: We now require CUB for building, here we make the tutorials include it. Also make the installation cell do nothing if it has already succeeded. I use curl not wget, and `os.environ` to set the variables not shell methods, because they are more likely to work on Windows. Reviewed By: nikhilaravi Differential Revision: D24860574 fbshipit-source-id: 5be86af15e53f8db016ee0e96fb43153bd69adbc
Tutorial notebooks
For current versions of the tutorials, which correspond to the latest release,
please look at this directory at the stable
tag, namely at
https://github.com/facebookresearch/pytorch3d/tree/stable/docs/tutorials .
There are links at the project homepage for opening these directly in colab.
They install torch, torchvision and PyTorch3D from pip, which should work with the CUDA 10.1 inside a GPU colab notebook. If you need to install PyTorch3D from source inside colab, you can use
import os
!curl -O https://github.com/NVIDIA/cub/archive/1.10.0.tar.gz
!tar xzf 1.10.0.tar.gz
os.environ["CUB_HOME"] = os.getcwd() + "/cub-1.10.0"
!pip install 'git+https://github.com/facebookresearch/pytorch3d.git@stable'`
instead.
The versions of these tutorials on the main branch may need to use the latest
PyTorch3D from the main branch. You may be able to install this from source
with the same commands as above, but replacing the last line with
!pip install 'git+https://github.com/facebookresearch/pytorch3d.git'
.