matteo-dunnhofer / imagenet

TensorFlow implementation of AlexNet and its training and testing on ImageNet ILSVRC 2012 dataset

AlexNet training on ImageNet LSVRC 2012

This repository contains an implementation of AlexNet convolutional neural network and its training and testing procedures on the ILSVRC 2012 dataset, all using TensorFlow.

Folder tf contains code in the "classic TensorFlow" framework whereas code in the tf_eager directory has been developed with TensorFlow's new impearative style, TensorFlow eager.

The two implementations are independent and refer to the READMEs inside the folders for specific instruction on how to train and to test.

References

• Alex Krizhevsky, Ilya Sutskever and Geoffrey E. Hinton. ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Inforamtion Processing Systems 25, 2012.
• Olga Russakovsky°, Jia Deng°, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg and Li Fei-Fei. (° = equal contribution) ImageNet Large Scale Visual Recognition Challenge. IJCV, 2015