Comments (1)
Hi again.
I've managed to progress a bit in my attempt to run BUDDI. I had to install some additional packages.
# Eventually update conda
# conda update conda
conda create -n hhcenv39 python=3.9
conda activate hhcenv39
conda install -c pytorch pytorch=1.9.1 torchvision cudatoolkit=10.2
conda install -c fvcore -c iopath -c conda-forge fvcore iopath
conda install -c bottler nvidiacub
conda install pytorch3d -c pytorch3d
conda install -c conda-forge tensorboard
pip install opencv-python smplx scipy scikit-image loguru omegaconf ipdb einops chumpy trimesh setuptools==58.2.0
+ conda install -c conda-forge gcc==12.3.0
+ conda install -c conda-forge gxx==12.3.0
conda run -n hhcenv39 --live-stream pip install 'git+https://github.com/facebookresearch/detectron2.git'
pip install mmcv==1.3.9 timm
pip install -v -e third-party/ViTPose/
pip install simple_romp==1.1.3
+ pip install pyrender
+ pip install wandb
gxx
was needed for the install of detectron2
to work. I'm not fully sure about gcc
though.
pyrender
and wandb
dependencies arose when trying to run the script as stated below.
Then I tried running the script as stated in the README
python llib/methods/hhc_diffusion/evaluation/sample.py --exp-cfg essentials/buddi/buddi_unconditional.yaml --output-folder demo/diffusion/samples/ --checkpoint-name essentials/buddi/buddi_unconditional.pt --max-images-render=100 --num-samples 100 --max-t 1000 --skip-steps 10 --log-steps=100 --save-vis
However, the environment is still not correct.
First, it complains about some NumPy problem:
A module that was compiled using NumPy 1.x cannot be run in
NumPy 2.0.0 as it may crash. To support both 1.x and 2.x
versions of NumPy, modules must be compiled with NumPy 2.0.
Some module may need to rebuild instead e.g. with 'pybind11>=2.12'.
If you are a user of the module, the easiest solution will be to
downgrade to 'numpy<2' or try to upgrade the affected module.
We expect that some modules will need time to support NumPy 2.
Then, another problem arises, some kind of incompatibility between my GPU, my CUDA install and the installed PyTorch version:
Traceback (most recent call last): File "/home/my_linux_user/buddienv/buddi/llib/methods/hhc_diffusion/evaluation/sample.py", line 12, in <module>
import torch
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/__init__.py", line 629, in <module>
from .functional import * # noqa: F403
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/functional.py", line 6, in <module>
import torch.nn.functional as F
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/nn/__init__.py", line 1, in <module>
from .modules import * # noqa: F403
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/nn/modules/__init__.py", line 2, in <module>
from .linear import Identity, Linear, Bilinear, LazyLinear
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/nn/modules/linear.py", line 6, in <module>
from .. import functional as F
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/nn/functional.py", line 11, in <module>
from .._jit_internal import boolean_dispatch, _overload, BroadcastingList1, BroadcastingList2, BroadcastingList3
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/_jit_internal.py", line 26, in <module>
import torch.package._mangling as package_mangling
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/package/__init__.py", line 12, in <module>
from .package_importer import PackageImporter
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/package/package_importer.py", line 26, in <module>
from ._mock_zipreader import MockZipReader
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/package/_mock_zipreader.py", line 17, in <module>
_dtype_to_storage = {data_type(0).dtype: data_type for data_type in _storages}
File "/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/package/_mock_zipreader.py", line 17, in <dictcomp>
_dtype_to_storage = {data_type(0).dtype: data_type for data_type in _storages}
/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/package/_mock_zipreader.py:17: UserWarning: Failed to initialize NumPy: _ARRAY_API not found (Triggered internally at /opt/conda/conda-bld/pytorch_1631630797748/work/torch/csrc/utils/tensor_numpy.cpp:67.)
_dtype_to_storage = {data_type(0).dtype: data_type for data_type in _storages}
FOUND 0 matches for demo/diffusion/samples/generate_1000_10
/home/my_linux_user/.conda/envs/hhcenv39/lib/python3.9/site-packages/torch/cuda/__init__.py:106: UserWarning:
NVIDIA GeForce RTX 3080 Ti with CUDA capability sm_86 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_37 sm_50 sm_60 sm_61 sm_70 sm_75 compute_37.
If you want to use the NVIDIA GeForce RTX 3080 Ti GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
warnings.warn(incompatible_device_warn.format(device_name, capability, " ".join(arch_list), device_name))
I hope this helps in fixing/updating the dependencies.
from buddi.
Related Issues (10)
- Pseudo-ground truth fits URL link 404 HOT 3
- Evaluation on Hi4D? HOT 1
- Tracking single person
- Missing Functions in llib/methods/hhc_diffusion/evaluation/sample.py( build_renderer, render_360_views and eval_diffusion) HOT 1
- can you show a video demo? HOT 2
- demo on custom data HOT 1
- Missing pseudo ground-truth fits for FlickrCI3D and auxiliary data (train_val_split.npz, train_pgt.pkl and val_pgt.pkl) HOT 2
- 🦒 colab HOT 2
- Data splits for all datasets HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from buddi.