Invariance, Same-Equivariance and other measures for Neural Networks. Support for PyTorch (now) and TensorFlow (coming).
Project description
Transformational Measures
The Transformational Measures (TM) library allows neural network designers to evaluate the invariance, equivariance and other properties of their models with respect to a set of transformations. Support for Pytorch (current) and Tensorflow/Keras (coming).
Visualizations
Invariance heatmap: Each column shows the invariance to rotation of a layer of a Neural Network. Each row/block inside each column indicates the invariance of a feature map or single neuron, depending on the layer.
Invariance vs layer, same model: Plot of the transformational and sample invariance to rotations of a simple neural network trained on MNIST, with and without data augmentation. The X axis indicates the layer, while the Y axis shows the average invariance of the layer.
Invariance vs layer, different models: Plot of the invariance to rotations of several well-known models trained on CIFAR10. The number of layers of each model is fit on a percentage scale, so that different models can be compared
PyTorch API
TODO describe
TensorFlow API
Examples
You can find many uses of this library in the repository with the code for the article Measuring (in)variances in Convolutional Networks, where this library was first presented. Also, in the code for the experiments of the PhD Thesis "Invariance and Same-Equivariance Measures for Convolutional Neural Networks" (spanish).
Citing
If you use this library in your research, we kindly ask you to cite Measuring (in)variances in Convolutional Networks
Bibtex
@inproceedings{quiroga2019measuring,
title={Measuring (in) variances in Convolutional Networks},
author={Quiroga, Facundo and Torrents-Barrena, Jordina and Lanzarini, Laura and Puig, Domenec},
booktitle={Conference on Cloud Computing and Big Data},
pages={98--109},
year={2019},
organization={Springer}
}
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
Built Distribution
Hashes for tmeasures-0.1a0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | aa72c4cee4594fd918994cb623e77b60d4572b693afe2e67dbf20b09873a77f4 |
|
MD5 | da1946e9d22e0ee35296c3bab081ba73 |
|
BLAKE2b-256 | 04be6c4cf6e5dd30b32704bc210c63da8ad251b9410739d7db7f8621d9399086 |