kwea123 / nerf_pl

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

Home Page:https://www.youtube.com/playlist?list=PLDV2CyUo4q-K02pNEyDr7DYpTQuka3mbV

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

nerf colab run with error

JianingHe0115 opened this issue · comments

When I run the in installation part of the nerf in colab, there are some error about the torch version.

Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
ERROR: Could not find a version that satisfies the requirement torch==1.4.0 (from versions: 1.7.1, 1.8.0, 1.8.1, 1.9.0, 1.9.1, 1.10.0, 1.10.1, 1.10.2, 1.11.0, 1.12.0, 1.12.1, 1.13.0, 1.13.1, 2.0.0)
ERROR: No matching distribution found for torch==1.4.0

And I change the torch version, there are some error about training part:
/content/nerf_pl
Traceback (most recent call last):
File "/content/nerf_pl/train.py", line 7, in
from datasets import dataset_dict
File "/content/nerf_pl/datasets/init.py", line 1, in
from .blender import BlenderDataset
File "/content/nerf_pl/datasets/blender.py", line 9, in
from .ray_utils import *
File "/content/nerf_pl/datasets/ray_utils.py", line 2, in
from kornia import create_meshgrid
File "/usr/local/lib/python3.9/dist-packages/kornia/init.py", line 12, in
from kornia import augmentation
File "/usr/local/lib/python3.9/dist-packages/kornia/augmentation/init.py", line 1, in
from .augmentation import *
File "/usr/local/lib/python3.9/dist-packages/kornia/augmentation/augmentation.py", line 7, in
from . import functional as F
File "/usr/local/lib/python3.9/dist-packages/kornia/augmentation/functional.py", line 488
input = input.view((-1, (*input.shape[-3:])))
^
SyntaxError: can't use starred expression here

AFAIK, I think torch <= 1.6 doesn't support in python 3.9. Google colab uses python 3.9. So, my suggestion is using torch that supported by python 3.9, but please don't use torch 2.0 since some dependencies don't compatible with it.

before git clone, use the command
! sudo update-alternatives --config python3
then, select the python3.8