Comments (2)
Hello, I have encountered the same issue as you regarding ‘pointnet2_ batch_cuda‘, Have you resolved the issue with the module now?
from pointmetabase.
I decided to use docker to solve it.
Docker image: pytorch/pytorch:1.10.0-cuda11.3-cudnn8-devel
Install in the container this in a .sh:
# python, pytorch and cuda already installed in docker image
# activate environment
conda activate
# install relevant packages
# torch-scatter is a must, and others are optional
pip install torch-scatter -f https://data.pyg.org/whl/torch-1.10.1+cu113.html
# pip install torch-scatter torch-sparse torch-cluster torch-geometric -f https://data.pyg.org/whl/torch-1.10.1+cu113.html
pip install -r requirements.txt
# install cpp extensions, the pointnet++ library
cd openpoints/cpp/pointnet2_batch
python setup.py install
cd ../
# grid_subsampling library. necessary only if interested in S3DIS_sphere
cd subsampling
python setup.py build_ext --inplace
cd ..
# # point transformer library. Necessary only if interested in Point Transformer and Stratified Transformer
cd pointops/
python setup.py install
cd ..
# Blow are functions that optional. Necessary only if interested in reconstruction tasks such as completion
cd chamfer_dist
python setup.py install --user
cd ../emd
python setup.py install --user
cd ../../../
Being the requirements:
scikit-learn==1.0.2
pickleshare==0.7.5
ninja==1.10.2.3
gdown==4.7.1 # The version was not specified
easydict==1.9
PyYAML==6.0
protobuf==3.19.4
tensorboard==2.8.0
termcolor==1.1.0
tqdm==4.62.3
multimethod==1.7
h5py==3.6.0
matplotlib==3.5.1
wandb==0.15.2 # The version was not specified
pyvista==0.33.2
setuptools==59.5.0
Cython==0.29.28
pandas==1.3.5 # The version was not specified
shortuuid==1.0.11 # It was not in the original requirements.txt but it was needed when executing
# for docs
mkdocs-material==9.1.11 # The version was not specified
mkdocs-awesome-pages-plugin==2.9.1 # The version was not specified
mdx_truly_sane_lists==1.3 # The version was not specified
from pointmetabase.
Related Issues (20)
- pretrained model of PointMetaBase-XXL on S3DIS 6-fold HOT 1
- Result of PointNeXt in scannet. HOT 1
- About the pretrained link for pointmetabase-xxl trained on scannet HOT 1
- Does the preprocessing method of data affect the accuracy of the network? HOT 2
- About the torch seed configuration in the code HOT 1
- How to preprocess and test my own data
- Downloading and evaluate the dataset
- pretrained model of PointMetaBase-XXL on ScanNet
- About Throught
- About Throughtput
- code version HOT 1
- FileNotFoundError: S3DIS: [Errno 2] No such file or directory
- val miou high but test miou low HOT 8
- Ablation study on S3DIS HOT 2
- val on S3DIS but CUDA out of memory HOT 4
- How visualization HOT 8
- Pointnet++ implementation for ShapeNet Part Segmentation
- can you write pointtransformer.yaml for s3dis HOT 1
- CUDA_VISIBLE_DEVICES=0 bash script/main_segmentation.sh cfgs/s3dis/pointmetabase-l.yaml HOT 1
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 pointmetabase.