alexisbcook / keras_transfer_cifar10

Object classification with CIFAR-10 using transfer learning

Keras Transfer Learning on CIFAR-10

In the Jupyter notebook for this repository, I begin by calculating the bottleneck features for the CIFAR-10 dataset.

These features are then visualized with a Barnes-Hut implementation of t-SNE, which is the fastest t-SNE implementation to date.

For Python >= 3.5, this implementation can be installed by running

pip install git+https://github.com/alexisbcook/tsne.git

The bottleneck features are then fed to a shallow CNN for image classification. The model attains a test accuracy of 82.68%.

Blog Post

This repository is discussed in the blog post here.

About

Object classification with CIFAR-10 using transfer learning

keras keras-neural-networks keras-models keras-classification-models keras-visualization images image-classification classification classifier classification-algorithm cnn cnn-keras cnn-model cnn-architecture convolutional-neural-networks convolutional-networks tsne tsne-algorithm visualization transfer-learning

Languages

Language:Jupyter Notebook 100.0%