Metadata-Version: 2.1
Name: WeightWatcher
Version: 0.1
Summary: Analyze weight matrices of Deep Neural Networks
Home-page: https://calculationconsulting.com/
Author: Calculation Consulting
Author-email: info@calculationconsulting.com
Maintainer: Calculation Consulting
Maintainer-email: info@calculationconsulting.com
License: Apache License, Version 2.0
Project-URL: Documentation, https://calculationconsulting.com/
Project-URL: Code, https://github.com/calculatedcontent/weightwatcher
Project-URL: Issue tracker, https://github.com/calculationconsulting/weightwatcher/issues
Keywords: Deep Learning Keras Tensorflow pytorch CNN DNN Neural Networks
Platform: UNKNOWN
Requires-Python: >=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: matplotlib
Requires-Dist: powerlaw
Requires-Dist: tensorflow
Requires-Dist: keras
Requires-Dist: sklearn

## Weight Watcher

**Weight Watcher** analyzes weight matrices of Deep Neural Networks.

## Installation

```sh
pip install weightwatcher
```

## Usage

Weight Watcher works with both Keras and pyTorch models.

```python
import weightwatcher as ww
watcher = ww.WeightWatcher(model=model)
results = watcher.analyze()

watcher.get_summary()
watcher.print_results()
```

## Links

[Weight Watcher homepage](https://calculationconsulting.com)

## License

[Apache License 2.0](LICENSE)


