Skip to content

GitLab

Commit e4a899d4 authored by yangzhong's avatar yangzhong
Browse files

修改README格式

parent 4d4e064b
Hide whitespace changes
Inline Side-by-side
Showing with 47 additions and 295 deletions
README.md
View file @ e4a899d4
[pypi-image]: https://badge.fury.io/py/torch-cluster.svg # <div align="center"><strong>PyTorch Cluster</strong></div>
[pypi-url]: https://pypi.python.org/pypi/torch-cluster ## 简介
[testing-image]: https://github.com/rusty1s/pytorch_cluster/actions/workflows/testing.yml/badge.svg PyTorch Cluster由一个高度优化的图聚类算法的小型扩展库组成，用于PyTorch。PyTorch Cluster官方github地址:[https://github.com/rusty1s/pytorch_cluster](https://github.com/rusty1s/pytorch_cluster)
[testing-url]: https://github.com/rusty1s/pytorch_cluster/actions/workflows/testing.yml
[linting-image]: https://github.com/rusty1s/pytorch_cluster/actions/workflows/linting.yml/badge.svg ## 安装
[linting-url]: https://github.com/rusty1s/pytorch_cluster/actions/workflows/linting.yml
[coverage-image]: https://codecov.io/gh/rusty1s/pytorch_cluster/branch/master/graph/badge.svg ### 使用pip方式安装
[coverage-url]: https://codecov.io/github/rusty1s/pytorch_cluster?branch=master pytorch-cluster whl包下载目录：[http://10.6.10.68:8000/customized/torch-cluster/dtk2310](http://10.6.10.68:8000/customized/torch-cluster/dtk2310)，目前只提供有python3.8版本的whl包。
```shell
# PyTorch Cluster pip install torch_cluster* (下载的torch_cluster的whl包)
```
[![PyPI Version][pypi-image]][pypi-url] ### 使用源码编译方式安装
[![Testing Status][testing-image]][testing-url]
[![Linting Status][linting-image]][linting-url] #### 编译环境准备
[![Code Coverage][coverage-image]][coverage-url] - 安装相关依赖
```shell
-------------------------------------------------------------------------------- pip install numpy
pip install 'urllib3==1.26.14'
This package consists of a small extension library of highly optimized graph cluster algorithms for the use in [PyTorch](http://pytorch.org/). pip install pytest
The package consists of the following clustering algorithms: pip install wheel
```
* **[Graclus](#graclus)** from Dhillon *et al.*: [Weighted Graph Cuts without Eigenvectors: A Multilevel Approach](http://www.cs.utexas.edu/users/inderjit/public_papers/multilevel_pami.pdf) (PAMI 2007) - 在首页 | 光合开发者社区下载 dtk23.10 解压至 /opt/ 路径下，并建立软链接
* **[Voxel Grid Pooling](#voxelgrid)** from, *e.g.*, Simonovsky and Komodakis: [Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs](https://arxiv.org/abs/1704.02901) (CVPR 2017) ```shell
* **[Iterative Farthest Point Sampling](#farthestpointsampling)** from, *e.g.* Qi *et al.*: [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://arxiv.org/abs/1706.02413) (NIPS 2017) cd /opt && ln -s dtk-23.10 dtk
* **[k-NN](#knn-graph)** and **[Radius](#radius-graph)** graph generation source /opt/dtk/env.sh
* Clustering based on **[Nearest](#nearest)** points ```
* **[Random Walk Sampling](#randomwalk-sampling)** from, *e.g.*, Grover and Leskovec: [node2vec: Scalable Feature Learning for Networks](https://arxiv.org/abs/1607.00653) (KDD 2016) - 安装pytorch，pytorch whl包下载目录：[http://10.6.10.68:8000/debug/pytorch/dtk23.10/hipify/](http://10.6.10.68:8000/debug/pytorch/dtk23.10/hipify/)，根据python、dtk版本,下载对应pytorch的whl包。安装命令如下：
```shell
All included operations work on varying data types and are implemented both for CPU and GPU. pip install torch* (下载的torch的whl包)
```
## Installation #### 源码编译安装
```shell
### Anaconda git clone -b 1.6.0-release http://developer.hpccube.com/codes/aicomponent/torch-cluster.git
python pymap_script.py /path/to/pytorch_cluster
**Update:** You can now install `pytorch-cluster` via [Anaconda](https://anaconda.org/pyg/pytorch-cluster) for all major OS/PyTorch/CUDA combinations 🤗 cd pytorch_cluster
Given that you have [`pytorch >= 1.8.0` installed](https://pytorch.org/get-started/locally/), simply run python setup.py bdist_wheel
pip install dist/*.whl
```
conda install pytorch-cluster -c pyg
```
### Binaries
We alternatively provide pip wheels for all major OS/PyTorch/CUDA combinations, see [here](https://data.pyg.org/whl).
#### PyTorch 1.11
To install the binaries for PyTorch 1.11.0, simply run
```
pip install torch-cluster -f https://data.pyg.org/whl/torch-1.11.0+${CUDA}.html
```
where `${CUDA}` should be replaced by either `cpu`, `cu102`, `cu113`, or `cu115` depending on your PyTorch installation.
| | `cpu` | `cu102` | `cu113` | `cu115` |
|-------------|-------|---------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | | ✅ | ✅ |
| **macOS** | ✅ | | | |
#### PyTorch 1.10
To install the binaries for PyTorch 1.10.0, PyTorch 1.10.1 and PyTorch 1.10.2, simply run
```
pip install torch-cluster -f https://data.pyg.org/whl/torch-1.10.0+${CUDA}.html
```
where `${CUDA}` should be replaced by either `cpu`, `cu102`, `cu111`, or `cu113` depending on your PyTorch installation.
| | `cpu` | `cu102` | `cu111` | `cu113` |
|-------------|-------|---------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | ✅ | ✅ | ✅ |
| **macOS** | ✅ | | | |
**Note:** Binaries of older versions are also provided for PyTorch 1.4.0, PyTorch 1.5.0, PyTorch 1.6.0, PyTorch 1.7.0/1.7.1, PyTorch 1.8.0/1.8.1 and PyTorch 1.9.0 (following the same procedure).
For older versions, you might need to explicitly specify the latest supported version number in order to prevent a manual installation from source.
You can look up the latest supported version number [here](https://data.pyg.org/whl).
### From source
Ensure that at least PyTorch 1.4.0 is installed and verify that `cuda/bin` and `cuda/include` are in your `$PATH` and `$CPATH` respectively, *e.g.*:
```
$ python -c "import torch; print(torch.__version__)"
>>> 1.4.0
$ python -c "import torch; print(torch.__version__)"
>>> 1.1.0
$ echo $PATH
>>> /usr/local/cuda/bin:...
$ echo $CPATH
>>> /usr/local/cuda/include:...
```
Then run:
```
pip install torch-cluster
```
When running in a docker container without NVIDIA driver, PyTorch needs to evaluate the compute capabilities and may fail.
In this case, ensure that the compute capabilities are set via `TORCH_CUDA_ARCH_LIST`, *e.g.*:
```
export TORCH_CUDA_ARCH_LIST = "6.0 6.1 7.2+PTX 7.5+PTX"
```
## Functions
### Graclus
A greedy clustering algorithm of picking an unmarked vertex and matching it with one its unmarked neighbors (that maximizes its edge weight).
The GPU algorithm is adapted from Fagginger Auer and Bisseling: [A GPU Algorithm for Greedy Graph Matching](http://www.staff.science.uu.nl/~bisse101/Articles/match12.pdf) (LNCS 2012)
```python
import torch
from torch_cluster import graclus_cluster
row = torch.tensor([0, 1, 1, 2])
col = torch.tensor([1, 0, 2, 1])
weight = torch.tensor([1., 1., 1., 1.]) # Optional edge weights.
cluster = graclus_cluster(row, col, weight)
```
```
print(cluster)
tensor([0, 0, 1])
```
### VoxelGrid
A clustering algorithm, which overlays a regular grid of user-defined size over a point cloud and clusters all points within a voxel.
```python
import torch
from torch_cluster import grid_cluster
pos = torch.tensor([[0., 0.], [11., 9.], [2., 8.], [2., 2.], [8., 3.]])
size = torch.Tensor([5, 5])
cluster = grid_cluster(pos, size)
```
```
print(cluster)
tensor([0, 5, 3, 0, 1])
```
### FarthestPointSampling
A sampling algorithm, which iteratively samples the most distant point with regard to the rest points.
```python
import torch
from torch_cluster import fps
x = torch.tensor([[-1., -1.], [-1., 1.], [1., -1.], [1., 1.]])
batch = torch.tensor([0, 0, 0, 0])
index = fps(x, batch, ratio=0.5, random_start=False)
```
```
print(index)
tensor([0, 3])
```
### kNN-Graph
Computes graph edges to the nearest *k* points.
**Args:**
* **x** *(Tensor)*: Node feature matrix of shape `[N, F]`.
* **k** *(int)*: The number of neighbors.
* **batch** *(LongTensor, optional)*: Batch vector of shape `[N]`, which assigns each node to a specific example. `batch` needs to be sorted. (default: `None`)
* **loop** *(bool, optional)*: If `True`, the graph will contain self-loops. (default: `False`)
* **flow** *(string, optional)*: The flow direction when using in combination with message passing (`"source_to_target"` or `"target_to_source"`). (default: `"source_to_target"`)
* **cosine** *(boolean, optional)*: If `True`, will use the Cosine distance instead of Euclidean distance to find nearest neighbors. (default: `False`)
* **num_workers** *(int)*: Number of workers to use for computation. Has no effect in case `batch` is not `None`, or the input lies on the GPU. (default: `1`)
```python
import torch
from torch_cluster import knn_graph
x = torch.tensor([[-1., -1.], [-1., 1.], [1., -1.], [1., 1.]])
batch = torch.tensor([0, 0, 0, 0])
edge_index = knn_graph(x, k=2, batch=batch, loop=False)
```
```
print(edge_index)
tensor([[1, 2, 0, 3, 0, 3, 1, 2],
[0, 0, 1, 1, 2, 2, 3, 3]])
```
### Radius-Graph
Computes graph edges to all points within a given distance.
**Args:**
* **x** *(Tensor)*: Node feature matrix of shape `[N, F]`.
* **r** *(float)*: The radius.
* **batch** *(LongTensor, optional)*: Batch vector of shape `[N]`, which assigns each node to a specific example. `batch` needs to be sorted. (default: `None`)
* **loop** *(bool, optional)*: If `True`, the graph will contain self-loops. (default: `False`)
* **max_num_neighbors** *(int, optional)*: The maximum number of neighbors to return for each element. If the number of actual neighbors is greater than `max_num_neighbors`, returned neighbors are picked randomly. (default: `32`)
* **flow** *(string, optional)*: The flow direction when using in combination with message passing (`"source_to_target"` or `"target_to_source"`). (default: `"source_to_target"`)
* **num_workers** *(int)*: Number of workers to use for computation. Has no effect in case `batch` is not `None`, or the input lies on the GPU. (default: `1`)
```python
import torch
from torch_cluster import radius_graph
x = torch.tensor([[-1., -1.], [-1., 1.], [1., -1.], [1., 1.]])
batch = torch.tensor([0, 0, 0, 0])
edge_index = radius_graph(x, r=2.5, batch=batch, loop=False)
```
```
print(edge_index)
tensor([[1, 2, 0, 3, 0, 3, 1, 2],
[0, 0, 1, 1, 2, 2, 3, 3]])
```
### Nearest
Clusters points in *x* together which are nearest to a given query point in *y*.
`batch_{x,y}` vectors need to be sorted.
```python
import torch
from torch_cluster import nearest
x = torch.Tensor([[-1, -1], [-1, 1], [1, -1], [1, 1]])
batch_x = torch.tensor([0, 0, 0, 0])
y = torch.Tensor([[-1, 0], [1, 0]])
batch_y = torch.tensor([0, 0])
cluster = nearest(x, y, batch_x, batch_y)
```
```
print(cluster)
tensor([0, 0, 1, 1])
```
### RandomWalk-Sampling
Samples random walks of length `walk_length` from all node indices in `start` in the graph given by `(row, col)`.
```python
import torch
from torch_cluster import random_walk
row = torch.tensor([0, 1, 1, 1, 2, 2, 3, 3, 4, 4])
col = torch.tensor([1, 0, 2, 3, 1, 4, 1, 4, 2, 3])
start = torch.tensor([0, 1, 2, 3, 4])
walk = random_walk(row, col, start, walk_length=3)
```
```
print(walk)
tensor([[0, 1, 2, 4],
[1, 3, 4, 2],
[2, 4, 2, 1],
[3, 4, 2, 4],
[4, 3, 1, 0]])
```
## Running tests
``` ```
## 单测
```shell
cd pytorch_cluster
pytest pytest
``` ```
## Known Issue
## C++ API 完成安装进行单测时，会报错ImportError: Could not find module '_version_cpu' ~，在根目录/下查找一下，然后把库文件目录添加一下软链接即可。
`torch-cluster` also offers a C++ API that contains C++ equivalent of python models.
``` ```
mkdir build find / -name "_version_cpu.so"
cd build cd /pytorch_cluster/torch_cluster
# Add -DWITH_CUDA=on support for the CUDA if needed ln -s /usr/local/lib/python3.8/site-packages/torch_cluster/* .
cmake ..
make
make install
``` ```
### Compile the python library ## 参考资料
you can compile the Python wrapper which uses [pybind11](https://github.com/pybind/pybind11). This step requires the Python development libraries to be installed on the system.
```
python setup.py bdist_wheel
pip install dist/*.whl
```
https://github.com/rusty1s/pytorch_cluster
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment