Skip to content

GitLab

Commit 095cf6ce authored by limm's avatar limm
Browse files

add README.md

parent 04d6ec40
Hide whitespace changes
Inline Side-by-side
Showing with 243 additions and 184 deletions
README.md
View file @ 095cf6ce
[pypi-image]: https://badge.fury.io/py/torch-spline-conv.svg # <div aligh="center"><strong>PyTorch Spline Conv</strong></div>
[pypi-url]: https://pypi.python.org/pypi/torch-spline-conv ## 简介
[build-image]: https://travis-ci.org/rusty1s/pytorch_spline_conv.svg?branch=master Pytorch Spline Conv 是 SplineCNN 的基于样条的卷积算子
[build-url]: https://travis-ci.org/rusty1s/pytorch_spline_conv
[coverage-image]: https://codecov.io/gh/rusty1s/pytorch_spline_conv/branch/master/graph/badge.svg ### 使用pip方式安装
[coverage-url]: https://codecov.io/github/rusty1s/pytorch_spline_conv?branch=master pytorch-spline-conv whl包下载目录：[http://10.6.10.68:8000/customized/torch-spline-conv/dtk2310](http://10.6.10.68:8000/customized/torch-spline-conv/dtk2310). 目前只提供有python3.8版本的安装包
```shell
# Spline-Based Convolution Operator of SplineCNN pip install torch_spline_conv* (下载的torch_spine_conv的whl包)
```
[![PyPI Version][pypi-image]][pypi-url] ### 使用源码编译方式安装
[![Build Status][build-image]][build-url]
[![Code Coverage][coverage-image]][coverage-url] #### 编译环境准备
- 安装相关依赖
-------------------------------------------------------------------------------- ```shell
pip install numpy
This is a PyTorch implementation of the spline-based convolution operator of SplineCNN, as described in our paper: pip install 'urllib3==1.26.14'
pip install pytest
Matthias Fey, Jan Eric Lenssen, Frank Weichert, Heinrich Müller: [SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels](https://arxiv.org/abs/1711.08920) (CVPR 2018) pip insta;; wheel
```
The operator works on all floating point data types and is implemented both for CPU and GPU. - 在首页 | 光合开发者社区下载 det23.10 解压在 /opt/ 路径下，并建立软连接，例如
```shell
## Installation cd /opt
wget http://10.6.10.68:8000/dtk-release/dtk23.10/CentOS7.6/DTK-23.10-CentOS7.6-x86_64.tar.gz
### Binaries tar -zxvf DTK-23.10-CentOS7.6-x86_64.tar.gz
ln -s dtk-23.10 dtk
We provide pip wheels for all major OS/PyTorch/CUDA combinations, see [here](https://pytorch-geometric.com/whl). source /opt/dtk/env.sh
```
#### PyTorch 1.7.0
- 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). 根据需求下载对应的版本，安装如下：
To install the binaries for PyTorch 1.7.0, simply run ```shell
pip install torch* (下载的torch的whl包)
``` ```
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.7.0+${CUDA}.html #### 源码下载编译安装
``` ```shell
git clone -b 1.2.1-release http://developer.hpccube.com/codes/aicomponent/torch-spline-conv.git
where `${CUDA}` should be replaced by either `cpu`, `cu92`, `cu101`, `cu102`, or `cu110` depending on your PyTorch installation. python pymap_script.py /path/to/pytorch_spline_conv
cd torch_spline_conv
| | `cpu` | `cu92` | `cu101` | `cu102` | `cu110` | python setup.py bdist_wheel
|-------------|-------|--------|---------|---------|---------| pip install dist/*.whl
| **Linux** | ✅ | ✅ | ✅ | ✅ | ✅ | ```
| **Windows** | ✅ | ❌ | ✅ | ✅ | ✅ |
| **macOS** | ✅ | | | | | ## 单侧
```shell
#### PyTorch 1.6.0 cd torch_spline_conv
python setup.py test
To install the binaries for PyTorch 1.6.0, simply run
```
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.6.0+${CUDA}.html
```
where `${CUDA}` should be replaced by either `cpu`, `cu92`, `cu101` or `cu102` depending on your PyTorch installation.
| | `cpu` | `cu92` | `cu101` | `cu102` |
|-------------|-------|--------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | ❌ | ✅ | ✅ |
| **macOS** | ✅ | | | |
**Note:** Binaries of older versions are also provided for PyTorch 1.4.0 and PyTorch 1.5.0 (following the same procedure).
### 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
$ echo $PATH
>>> /usr/local/cuda/bin:...
$ echo $CPATH
>>> /usr/local/cuda/include:...
```
Then run:
```
pip install torch-spline-conv
```
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"
```
## Usage
```python
from torch_spline_conv import spline_conv
out = spline_conv(x,
edge_index,
pseudo,
weight,
kernel_size,
is_open_spline,
degree=1,
norm=True,
root_weight=None,
bias=None)
```
Applies the spline-based convolution operator
<p align="center">
<img width="50%" src="https://user-images.githubusercontent.com/6945922/38684093-36d9c52e-3e6f-11e8-9021-db054223c6b9.png" />
</p>
over several node features of an input graph.
The kernel function is defined over the weighted B-spline tensor product basis, as shown below for different B-spline degrees.
<p align="center">
<img width="45%" src="https://user-images.githubusercontent.com/6945922/38685443-3a2a0c68-3e72-11e8-8e13-9ce9ad8fe43e.png" />
<img width="45%" src="https://user-images.githubusercontent.com/6945922/38685459-42b2bcae-3e72-11e8-88cc-4b61e41dbd93.png" />
</p>
### Parameters
* **x** *(Tensor)* - Input node features of shape `(number_of_nodes x in_channels)`.
* **edge_index** *(LongTensor)* - Graph edges, given by source and target indices, of shape `(2 x number_of_edges)`.
* **pseudo** *(Tensor)* - Edge attributes, ie. pseudo coordinates, of shape `(number_of_edges x number_of_edge_attributes)` in the fixed interval [0, 1].
* **weight** *(Tensor)* - Trainable weight parameters of shape `(kernel_size x in_channels x out_channels)`.
* **kernel_size** *(LongTensor)* - Number of trainable weight parameters in each edge dimension.
* **is_open_spline** *(ByteTensor)* - Whether to use open or closed B-spline bases for each dimension.
* **degree** *(int, optional)* - B-spline basis degree. (default: `1`)
* **norm** *(bool, optional)*: Whether to normalize output by node degree. (default: `True`)
* **root_weight** *(Tensor, optional)* - Additional shared trainable parameters for each feature of the root node of shape `(in_channels x out_channels)`. (default: `None`)
* **bias** *(Tensor, optional)* - Optional bias of shape `(out_channels)`. (default: `None`)
### Returns
* **out** *(Tensor)* - Out node features of shape `(number_of_nodes x out_channels)`.
### Example
```python
import torch
from torch_spline_conv import spline_conv
x = torch.rand((4, 2), dtype=torch.float) # 4 nodes with 2 features each
edge_index = torch.tensor([[0, 1, 1, 2, 2, 3], [1, 0, 2, 1, 3, 2]]) # 6 edges
pseudo = torch.rand((6, 2), dtype=torch.float) # two-dimensional edge attributes
weight = torch.rand((25, 2, 4), dtype=torch.float) # 25 parameters for in_channels x out_channels
kernel_size = torch.tensor([5, 5]) # 5 parameters in each edge dimension
is_open_spline = torch.tensor([1, 1], dtype=torch.uint8) # only use open B-splines
degree = 1 # B-spline degree of 1
norm = True # Normalize output by node degree.
root_weight = torch.rand((2, 4), dtype=torch.float) # separately weight root nodes
bias = None # do not apply an additional bias
out = spline_conv(x, edge_index, pseudo, weight, kernel_size,
is_open_spline, degree, norm, root_weight, bias)
print(out.size())
torch.Size([4, 4]) # 4 nodes with 4 features each
```
## Cite
Please cite our paper if you use this code in your own work:
```
@inproceedings{Fey/etal/2018,
title={{SplineCNN}: Fast Geometric Deep Learning with Continuous {B}-Spline Kernels},
author={Fey, Matthias and Lenssen, Jan Eric and Weichert, Frank and M{\"u}ller, Heinrich},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
}
``` ```
## Running tests ## Known Issue
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。
``` ```
python setup.py test find / -name "_version_cpu.so"
cd /torch_spline_conv/torch_spline_conv
ln -s /usr/local/lib/python3.8/site-packages/torch_spline_conv/* .
``` ```
## C++ API ## 参考资料
```shell
`torch-spline-conv` also offers a C++ API that contains C++ equivalent of python models. https://github.com/rusty1s/pytorch_spline_conv
```
mkdir build
cd build
# Add -DWITH_CUDA=on support for the CUDA if needed
cmake ..
make
make install
``` ```
README_BAK.md 0 → 100644
View file @ 095cf6ce
[pypi-image]: https://badge.fury.io/py/torch-spline-conv.svg
[pypi-url]: https://pypi.python.org/pypi/torch-spline-conv
[build-image]: https://travis-ci.org/rusty1s/pytorch_spline_conv.svg?branch=master
[build-url]: https://travis-ci.org/rusty1s/pytorch_spline_conv
[coverage-image]: https://codecov.io/gh/rusty1s/pytorch_spline_conv/branch/master/graph/badge.svg
[coverage-url]: https://codecov.io/github/rusty1s/pytorch_spline_conv?branch=master
# Spline-Based Convolution Operator of SplineCNN
[![PyPI Version][pypi-image]][pypi-url]
[![Build Status][build-image]][build-url]
[![Code Coverage][coverage-image]][coverage-url]
--------------------------------------------------------------------------------
This is a PyTorch implementation of the spline-based convolution operator of SplineCNN, as described in our paper:
Matthias Fey, Jan Eric Lenssen, Frank Weichert, Heinrich Müller: [SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels](https://arxiv.org/abs/1711.08920) (CVPR 2018)
The operator works on all floating point data types and is implemented both for CPU and GPU.
## Installation
### Binaries
We provide pip wheels for all major OS/PyTorch/CUDA combinations, see [here](https://pytorch-geometric.com/whl).
#### PyTorch 1.7.0
To install the binaries for PyTorch 1.7.0, simply run
```
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.7.0+${CUDA}.html
```
where `${CUDA}` should be replaced by either `cpu`, `cu92`, `cu101`, `cu102`, or `cu110` depending on your PyTorch installation.
| | `cpu` | `cu92` | `cu101` | `cu102` | `cu110` |
|-------------|-------|--------|---------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | ❌ | ✅ | ✅ | ✅ |
| **macOS** | ✅ | | | | |
#### PyTorch 1.6.0
To install the binaries for PyTorch 1.6.0, simply run
```
pip install torch-spline-conv -f https://pytorch-geometric.com/whl/torch-1.6.0+${CUDA}.html
```
where `${CUDA}` should be replaced by either `cpu`, `cu92`, `cu101` or `cu102` depending on your PyTorch installation.
| | `cpu` | `cu92` | `cu101` | `cu102` |
|-------------|-------|--------|---------|---------|
| **Linux** | ✅ | ✅ | ✅ | ✅ |
| **Windows** | ✅ | ❌ | ✅ | ✅ |
| **macOS** | ✅ | | | |
**Note:** Binaries of older versions are also provided for PyTorch 1.4.0 and PyTorch 1.5.0 (following the same procedure).
### From source
Ensure that at least PyTorch 1.4.0 is installed and verify that `cuda/bin` and `cuda/include` are in your `$PATH` and `$CPATH` respectively, *e.g.*:
```
$ python -c "import torch; print(torch.__version__)"
>>> 1.4.0
$ echo $PATH
>>> /usr/local/cuda/bin:...
$ echo $CPATH
>>> /usr/local/cuda/include:...
```
Then run:
```
pip install torch-spline-conv
```
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"
```
## Usage
```python
from torch_spline_conv import spline_conv
out = spline_conv(x,
edge_index,
pseudo,
weight,
kernel_size,
is_open_spline,
degree=1,
norm=True,
root_weight=None,
bias=None)
```
Applies the spline-based convolution operator
<p align="center">
<img width="50%" src="https://user-images.githubusercontent.com/6945922/38684093-36d9c52e-3e6f-11e8-9021-db054223c6b9.png" />
</p>
over several node features of an input graph.
The kernel function is defined over the weighted B-spline tensor product basis, as shown below for different B-spline degrees.
<p align="center">
<img width="45%" src="https://user-images.githubusercontent.com/6945922/38685443-3a2a0c68-3e72-11e8-8e13-9ce9ad8fe43e.png" />
<img width="45%" src="https://user-images.githubusercontent.com/6945922/38685459-42b2bcae-3e72-11e8-88cc-4b61e41dbd93.png" />
</p>
### Parameters
* **x** *(Tensor)* - Input node features of shape `(number_of_nodes x in_channels)`.
* **edge_index** *(LongTensor)* - Graph edges, given by source and target indices, of shape `(2 x number_of_edges)`.
* **pseudo** *(Tensor)* - Edge attributes, ie. pseudo coordinates, of shape `(number_of_edges x number_of_edge_attributes)` in the fixed interval [0, 1].
* **weight** *(Tensor)* - Trainable weight parameters of shape `(kernel_size x in_channels x out_channels)`.
* **kernel_size** *(LongTensor)* - Number of trainable weight parameters in each edge dimension.
* **is_open_spline** *(ByteTensor)* - Whether to use open or closed B-spline bases for each dimension.
* **degree** *(int, optional)* - B-spline basis degree. (default: `1`)
* **norm** *(bool, optional)*: Whether to normalize output by node degree. (default: `True`)
* **root_weight** *(Tensor, optional)* - Additional shared trainable parameters for each feature of the root node of shape `(in_channels x out_channels)`. (default: `None`)
* **bias** *(Tensor, optional)* - Optional bias of shape `(out_channels)`. (default: `None`)
### Returns
* **out** *(Tensor)* - Out node features of shape `(number_of_nodes x out_channels)`.
### Example
```python
import torch
from torch_spline_conv import spline_conv
x = torch.rand((4, 2), dtype=torch.float) # 4 nodes with 2 features each
edge_index = torch.tensor([[0, 1, 1, 2, 2, 3], [1, 0, 2, 1, 3, 2]]) # 6 edges
pseudo = torch.rand((6, 2), dtype=torch.float) # two-dimensional edge attributes
weight = torch.rand((25, 2, 4), dtype=torch.float) # 25 parameters for in_channels x out_channels
kernel_size = torch.tensor([5, 5]) # 5 parameters in each edge dimension
is_open_spline = torch.tensor([1, 1], dtype=torch.uint8) # only use open B-splines
degree = 1 # B-spline degree of 1
norm = True # Normalize output by node degree.
root_weight = torch.rand((2, 4), dtype=torch.float) # separately weight root nodes
bias = None # do not apply an additional bias
out = spline_conv(x, edge_index, pseudo, weight, kernel_size,
is_open_spline, degree, norm, root_weight, bias)
print(out.size())
torch.Size([4, 4]) # 4 nodes with 4 features each
```
## Cite
Please cite our paper if you use this code in your own work:
```
@inproceedings{Fey/etal/2018,
title={{SplineCNN}: Fast Geometric Deep Learning with Continuous {B}-Spline Kernels},
author={Fey, Matthias and Lenssen, Jan Eric and Weichert, Frank and M{\"u}ller, Heinrich},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2018},
}
```
## Running tests
```
python setup.py test
```
## C++ API
`torch-spline-conv` also offers a C++ API that contains C++ equivalent of python models.
```
mkdir build
cd build
# Add -DWITH_CUDA=on support for the CUDA if needed
cmake ..
make
make install
```
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