Metadata-Version: 2.1
Name: nonlocalpooling
Version: 2.0.0
Summary: Global-Wise Pooling Layers for PyTorch
Home-page: https://github.com/Dootmaan/NonLocalPooling
Author: Hongyi Wang
Author-email: whongyi@zju.edu.cn
Project-URL: Bug Tracker, https://github.com/Dootmaan/NonLocalPooling/issues
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.5
Description-Content-Type: text/markdown
License-File: LICENSE

# Non-Local Pooling

## Update 1.2.0

- Now you can determine the output channel just like all the other learnable pooling methods (former version force out_channel=in_channel). However, if you specify out_channel, MaxPool would not work then since they cannot be added together. Leave out_channel to None to make the module works like before.

---

To use NonLocalPooling for your PyTorch project:

## Step 1
```
pip install nonlocalpooling
```

## Step 2
```
from nonlocalpooling.pool import NonLocalPool2d, NonLocalPool3d
```

---

Non-Local Pooling can be used to substitue your original PyTorch pooling methods.
