tf-keras, make the average of model weight in same models
Project description
modelaverage
`modelaverage` is a pip package which make the average weight of model weight in `same models`, inspired by [Average weights in keras models](https://stackoverflow.com/questions/48212110/average-weights-in-keras-models). I created this pip package to use distributed computing environment like `kubernetes`.
Usage
pip install modelaverage
orgit clone https://github.com/graykode/modelaverage && python setup.py install
- using function
average(modellist)
- modellist : list of model file names.
- return : averaged weight model
Example
Please see example
import tensorflow as tf
from modelaverage import average
modellist = ['models/mnist1.h5', 'models/mnist2.h5', 'models/mnist3.h5', 'models/mnist4.h5', 'models/mnist5.h5',
'models/mnist6.h5', 'models/mnist7.h5', 'models/mnist8.h5', 'models/mnist9.h5']
averaged_model = average(modellist)
for w in averaged_model.get_weights():
print(w.shape)
Author
- Name : Tae Hwan Jung(@graykode)
- Email : nlkey2022@gmail.com
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
modelaverage-1.0.1.tar.gz
(2.1 kB
view hashes)
Built Distribution
modelaverage-1.0.1-py3.6.egg
(3.8 kB
view hashes)