安装torch-scatter

## Installation

### Binaries

We provide pip wheels for all major OS/PyTorch/CUDA combinations, see [here](https://pytorch-geometric.com/whl).

#### PyTorch 1.5.0

To install the binaries for PyTorch 1.5.0, simply run

```
pip install torch-scatter==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.5.0.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**   | ✅    |        |         |         |

#### PyTorch 1.4.0

To install the binaries for PyTorch 1.4.0, simply run

```
pip install torch-scatter==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.4.0.html
```

where `${CUDA}` should be replaced by either `cpu`, `cu92`, `cu100` or `cu101` depending on your PyTorch installation.

|             | `cpu` | `cu92` | `cu100` | `cu101` |
|-------------|-------|--------|---------|---------|
| **Linux**   | ✅    | ✅     | ✅      | ✅      |
| **Windows** | ✅    | ❌     | ❌      | ✅      |
| **macOS**   | ✅    |        |         |         |

### 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-scatter
```

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"
```

## Example

```py
import torch
from torch_scatter import scatter_max

src = torch.tensor([[2, 0, 1, 4, 3], [0, 2, 1, 3, 4]])
index = torch.tensor([[4, 5, 4, 2, 3], [0, 0, 2, 2, 1]])

out, argmax = scatter_max(src, index, dim=-1)
```

```
print(out)
tensor([[0, 0, 4, 3, 2, 0],
        [2, 4, 3, 0, 0, 0]])

print(argmax)
tensor([[5, 5, 3, 4, 0, 1]
        [1, 4, 3, 5, 5, 5]])
```

## Running tests

```
python setup.py test
```

## C++ API

`torch-scatter` 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
```