CONVOLUTIONAL KERNEL NETWORK

Re-implementation of Convolutional Kernel Network (CKN) from Mairal (2016) in Python based on the TensorFlow framework (https://www.tensorflow.org/).

Authors: Ghislain Durif
Credits: Alberto Bietti, Dexiong Chen, Julien Mairal, Daan Wynen
Copyright: 2017 Inria

If you encounter any issue when installing or using the 'ckntf' package, you can contact us at ckn.dev@inria.fr (for bug report, support, etc.).

The ckntf package is available under the BSD license. The additional miso_svm, spherical_kmeans and whitening packages are available under the GPL-v3 license.

Requirement:

• Python3.x

• Numpy, Scipy

• Tensorflow

• Python packages miso_svm, spherical_kmeans and whitening are required to run included tutorials and examples. They are available in the corresponding sub-folders (and require the MKL library that is available with the Anaconda Python distribution).

Installation

You can check the dedicated file.

Regarding packages miso_svm, spherical_kmeans and whitening, you can check the installation instructions in miso_svm/README.md, spherical_kmeans/README.md and whitening/README.md respectively.

Tutorial

NB: To run the tutorial, you need to download the Cifar10 data set (either or both version):

• the pre-whitened version cifar10_whitened.pkl from http://pascal.inrialpes.fr/data2/gdurif/cifar10_whitened.pkl
• the standard version cifar10_batches from http://pascal.inrialpes.fr/data2/gdurif/cifar10_batches.tar.gz You can either directly put the file cifar10_whitened.pkl and the directory cifar10_batches (after you extracted it with the command tar -zxvf cifar10_batches.tar.gz) in the ckntf/data sub-folder before installing the ckntf package (with python setup.py install), or you can store them somewhere else on your machine, and you will have to modify the tutorial examples (see unsupervised_example.py or supervised_example.py) to load the data with the correct path.

A tutorial is available as a sub-module ckntf.tutorials and a doc page. To replicate the following results that were presented in Mairal (2016), every details can be found on the dedicated page.

Results

Reproduction of the results from Mairal (2016) with the 'ckntf' python package. The results from the original paper (Mairal, 2016) were achieved using some cudnn-based Matlab code available at https://gitlab.inria.fr/mairal/ckn-cudnn-matlab.

Unsupervised CKN

Here is a summary of the results regarding unsupervised CKN on Cifar10 image data set, with online whitening but without data augmentation and/or model averaging.

Supervised CKN

Regarding supervised CKN model training (without data augmentation), the best results regarding prediction accuracy were achieved with a 14 layer CKN model. Details about the architectures that were used can be found here.

NB: The Matlab-based code was able to reach an accuracy of 90.5% with the 14 layer model on the pre-whitened Cifar10 data set. For unknow reasons (we did run extensive tests), the Tensorflow-based package 'ckntf' was only able to reach an accuracy of 88.50%. However, for smaller architectures (such as the 5 layer architecture defined in the tutorial), the 'ckntf' package was able to exactly reproduce the results from the Matlab-based code (accuracy of 81.5%).

For developpers

(on GNU/Linux and MacOs only)

• To build/install/test the package, see:

./dev_command.sh help

References

Mairal, J., 2016. End-to-end kernel learning with supervised convolutional kernel networks, in: Advances in Neural Information Processing Systems. pp. 1399–1407.