Awesome Open Source
Awesome Open Source

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%.

t-SNE

Blog Post

This repository is discussed in the blog post here.


Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
jupyter-notebook (6,196
visualization (811
keras (762
convolutional-neural-networks (451
cnn (396
classification (277
image-classification (178
images (169
transfer-learning (110
convolutional-networks (51
classifier (38
cnn-keras (30
keras-models (22
cnn-model (20
keras-neural-networks (19
tsne (15