Analyze weight matrices of Deep Neural Networks
Project description
Weight Watcher
Weight Watcher analyzes weight matrices of Deep Neural Networks.
Installation
pip install weightwatcher
Usage
Weight Watcher works with both Keras and pyTorch models.
import weightwatcher as ww
watcher = ww.WeightWatcher(model=model)
results = watcher.analyze()
watcher.get_summary()
watcher.print_results()
Links
License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
WeightWatcher-0.1.1.tar.gz
(176.5 kB
view hashes)
Built Distribution
Close
Hashes for WeightWatcher-0.1.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ba5a455bd27558a691118225e2f9f5df2c05c2fb59f0bec2b79d1264da9f7269 |
|
MD5 | 8a73d717dbf16af77d5fb3d72f4c522f |
|
BLAKE2b-256 | b1a6233097381d4426cc20201ac13b115814aced6c0068a36fa7bfa882c83301 |