threestudio
threestudio copied to clipboard
threestudio-project
Google Colab Notebook
@qtabdullah Try our Colab notebook here! It is now just a simple wrapper, but at least you don't have to setup the environment locally :)
Could you provide a screenshot of the error message? @qtabdullah
no error just a blank message
@qtabdullah Hi, I just fixed the issue. If you don't want to lose your current sessions, just replace login with interpreter_login in this block :)
@bennyguo i got an error here is log `Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/ Collecting git+https://github.com/KAIR-BAIR/[email protected] Cloning https://github.com/KAIR-BAIR/nerfacc.git (to revision v0.5.2) to /tmp/pip-req-build-724kgdxu Running command git clone --filter=blob:none --quiet https://github.com/KAIR-BAIR/nerfacc.git /tmp/pip-req-build-724kgdxu Running command git checkout -q d84cdf3afd7dcfc42150e0f0506db58a5ce62812 Resolved https://github.com/KAIR-BAIR/nerfacc.git to commit d84cdf3afd7dcfc42150e0f0506db58a5ce62812 Running command git submodule update --init --recursive -q Preparing metadata (setup.py) ... done Requirement already satisfied: rich>=12 in /usr/local/lib/python3.10/dist-packages (from nerfacc==0.5.2) (13.3.4) Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from nerfacc==0.5.2) (1.12.1) Requirement already satisfied: markdown-it-py<3.0.0,>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=12->nerfacc==0.5.2) (2.2.0) Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=12->nerfacc==0.5.2) (2.14.0) Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch->nerfacc==0.5.2) (4.5.0) Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py<3.0.0,>=2.2.0->rich>=12->nerfacc==0.5.2) (0.1.2) Building wheels for collected packages: nerfacc error: subprocess-exited-with-error
× python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip. Building wheel for nerfacc (setup.py) ... error ERROR: Failed building wheel for nerfacc Running setup.py clean for nerfacc Failed to build nerfacc ERROR: Could not build wheels for nerfacc, which is required to install pyproject.toml-based projects Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/ Collecting git+https://github.com/NVlabs/nvdiffrast.git Cloning https://github.com/NVlabs/nvdiffrast.git to /tmp/pip-req-build-_jkdkd3y Running command git clone --filter=blob:none --quiet https://github.com/NVlabs/nvdiffrast.git /tmp/pip-req-build-_jkdkd3y Resolved https://github.com/NVlabs/nvdiffrast.git to commit 335cfa6b33d785730a04283994214bed57884e87 Preparing metadata (setup.py) ... done Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from nvdiffrast==0.3.0) (1.22.4) Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/ Collecting git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch Cloning https://github.com/NVlabs/tiny-cuda-nn/ to /tmp/pip-req-build-wgyd93jo Running command git clone --filter=blob:none --quiet https://github.com/NVlabs/tiny-cuda-nn/ /tmp/pip-req-build-wgyd93jo Resolved https://github.com/NVlabs/tiny-cuda-nn/ to commit a77dc53ed770dd8ea6f78951d5febe175d0045e9 Running command git submodule update --init --recursive -q Preparing metadata (setup.py) ... done Building wheels for collected packages: tinycudann error: subprocess-exited-with-error
× python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip. Building wheel for tinycudann (setup.py) ... error ERROR: Failed building wheel for tinycudann Running setup.py clean for tinycudann Failed to build tinycudann ERROR: Could not build wheels for tinycudann, which is required to install pyproject.toml-based `projects``
Could you run pip install git+https://github.com/KAIR-BAIR/[email protected] as an individual command and give the error message?
Could you run
pip install git+https://github.com/KAIR-BAIR/[email protected]as an individual command and give the error message?
`Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/ Collecting git+https://github.com/KAIR-BAIR/[email protected] Cloning https://github.com/KAIR-BAIR/nerfacc.git (to revision v0.5.2) to /tmp/pip-req-build-k8uiv9fi Running command git clone --filter=blob:none --quiet https://github.com/KAIR-BAIR/nerfacc.git /tmp/pip-req-build-k8uiv9fi Running command git checkout -q d84cdf3afd7dcfc42150e0f0506db58a5ce62812 Resolved https://github.com/KAIR-BAIR/nerfacc.git to commit d84cdf3afd7dcfc42150e0f0506db58a5ce62812 Running command git submodule update --init --recursive -q Preparing metadata (setup.py) ... done Requirement already satisfied: rich>=12 in /usr/local/lib/python3.10/dist-packages (from nerfacc==0.5.2) (13.3.4) Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from nerfacc==0.5.2) (1.12.1) Requirement already satisfied: markdown-it-py<3.0.0,>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=12->nerfacc==0.5.2) (2.2.0) Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=12->nerfacc==0.5.2) (2.14.0) Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch->nerfacc==0.5.2) (4.5.0) Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py<3.0.0,>=2.2.0->rich>=12->nerfacc==0.5.2) (0.1.2) Building wheels for collected packages: nerfacc error: subprocess-exited-with-error
× python setup.py bdist_wheel did not run successfully. │ exit code: 1 ╰─> See above for output.
note: This error originates from a subprocess, and is likely not a problem with pip. Building wheel for nerfacc (setup.py) ... error ERROR: Failed building wheel for nerfacc Running setup.py clean for nerfacc Failed to build nerfacc ERROR: Could not build wheels for nerfacc, which is required to install pyproject.toml-based projects`
I haven't encountered such a problem on colab. What GPU model do you have? Could you give the output of nvidia-smi?
I haven't encountered such a problem on colab. What GPU model do you have? Could you give the output of
nvidia-smi?
+-----------------------------------------------------------------------------+ | NVIDIA-SMI 525.85.12 Driver Version: 525.85.12 CUDA Version: 12.0 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 Tesla T4 Off | 00000000:00:04.0 Off | 0 | | N/A 41C P8 9W / 70W | 0MiB / 15360MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | No running processes found | +-----------------------------------------------------------------------------+
Did you try to restart the environment? simply just quit and reopen the colab url
Did you try to restart the environment? simply just quit and reopen the colab url
didnt work
Seems an issue related to incompatible PyTorch versions. Fixed in the latest commit. Please create a new environment and it should work now.
U need run this command:
sudo apt update sudo apt upgrade sudo apt install libgl1-mesa-glx
Seems an issue related to incompatible PyTorch versions. Fixed in the latest commit. Please create a new environment and it should work now.
Traceback (most recent call last):
File "/content/threestudio/launch.py", line 168, in
Seems an issue related to incompatible PyTorch versions. Fixed in the latest commit. Please create a new environment and it should work now.
Traceback (most recent call last): File "/content/threestudio/launch.py", line 168, in main() File "/content/threestudio/launch.py", line 69, in main import pytorch_lightning as pl File "/usr/local/lib/python3.10/dist-packages/pytorch_lightning/init.py", line 26, in from pytorch_lightning.callbacks import Callback # noqa: E402 File "/usr/local/lib/python3.10/dist-packages/pytorch_lightning/callbacks/init.py", line 14, in from pytorch_lightning.callbacks.batch_size_finder import BatchSizeFinder File "/usr/local/lib/python3.10/dist-packages/pytorch_lightning/callbacks/batch_size_finder.py", line 24, in from pytorch_lightning.callbacks.callback import Callback File "/usr/local/lib/python3.10/dist-packages/pytorch_lightning/callbacks/callback.py", line 25, in from pytorch_lightning.utilities.types import STEP_OUTPUT File "/usr/local/lib/python3.10/dist-packages/pytorch_lightning/utilities/types.py", line 25, in from torchmetrics import Metric File "/usr/local/lib/python3.10/dist-packages/torchmetrics/init.py", line 14, in from torchmetrics import functional # noqa: E402 File "/usr/local/lib/python3.10/dist-packages/torchmetrics/functional/init.py", line 14, in from torchmetrics.functional.audio.pit import permutation_invariant_training, pit_permutate File "/usr/local/lib/python3.10/dist-packages/torchmetrics/functional/audio/init.py", line 14, in from torchmetrics.functional.audio.pit import permutation_invariant_training, pit_permutate # noqa: F401 File "/usr/local/lib/python3.10/dist-packages/torchmetrics/functional/audio/pit.py", line 22, in from torchmetrics.utilities.imports import _SCIPY_AVAILABLE File "/usr/local/lib/python3.10/dist-packages/torchmetrics/utilities/init.py", line 1, in from torchmetrics.utilities.checks import check_forward_full_state_property # noqa: F401 File "/usr/local/lib/python3.10/dist-packages/torchmetrics/utilities/checks.py", line 25, in from torchmetrics.utilities.data import select_topk, to_onehot File "/usr/local/lib/python3.10/dist-packages/torchmetrics/utilities/data.py", line 19, in from torchmetrics.utilities.imports import _TORCH_GREATER_EQUAL_1_12, _XLA_AVAILABLE File "/usr/local/lib/python3.10/dist-packages/torchmetrics/utilities/imports.py", line 112, in _TORCHVISION_GREATER_EQUAL_0_8: Optional[bool] = _compare_version("torchvision", operator.ge, "0.8.0") File "/usr/local/lib/python3.10/dist-packages/torchmetrics/utilities/imports.py", line 78, in _compare_version if not _module_available(package): File "/usr/local/lib/python3.10/dist-packages/torchmetrics/utilities/imports.py", line 59, in _module_available module = import_module(module_names[0]) File "/usr/lib/python3.10/importlib/init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "/usr/local/lib/python3.10/dist-packages/torchvision/init.py", line 6, in from torchvision import datasets, io, models, ops, transforms, utils File "/usr/local/lib/python3.10/dist-packages/torchvision/datasets/init.py", line 1, in from ._optical_flow import FlyingChairs, FlyingThings3D, HD1K, KittiFlow, Sintel File "/usr/local/lib/python3.10/dist-packages/torchvision/datasets/_optical_flow.py", line 12, in from ..io.image import _read_png_16 File "/usr/local/lib/python3.10/dist-packages/torchvision/io/init.py", line 8, in from ._load_gpu_decoder import _HAS_GPU_VIDEO_DECODER File "/usr/local/lib/python3.10/dist-packages/torchvision/io/_load_gpu_decoder.py", line 1, in from ..extension import _load_library File "/usr/local/lib/python3.10/dist-packages/torchvision/extension.py", line 107, in _check_cuda_version() File "/usr/local/lib/python3.10/dist-packages/torchvision/extension.py", line 80, in _check_cuda_version raise RuntimeError( RuntimeError: Detected that PyTorch and torchvision were compiled with different CUDA versions. PyTorch has CUDA Version=11.7 and torchvision has CUDA Version=11.8. Please reinstall the torchvision that matches your PyTorch install.
@bennyguo
The colab environment comes with torch2.0.1+cu118. I noticed that when installing xformers it forces a reinstallation of torch2.0.0 which is incompatible with torchvision comes with the environment ... I've removed xformers from the notebook as we don't need it anyway with torch>=2.0.0. Could you try again? Sorry for the inconvenience.
I recommend we close this issue since it's getting pretty long and it seems you solve most issues. People can open more precise issues if they encounter any.
