Keras Transfer Cifar10 Save
Object classification with CIFAR-10 using transfer learning
Project README
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.
Open Source Agenda is not affiliated with "Keras Transfer Cifar10" Project. README Source: alexisbcook/keras_transfer_cifar10
Stars
130
Open Issues
3
Last Commit
2 years ago
Repository
Tags
Classification
Classification Algorithm
Classifier
Cnn
Cnn Architecture
Cnn Keras
Cnn Model
Convolutional Networks
Convolutional Neural Networks
Image Classification
Images
Keras
Keras Classification Models
Keras Models
Keras Neural Networks
Keras Visualization
Transfer Learning
Tsne
Tsne Algorithm
Visualization
Open Source Agenda Badge
