AFAgarap/cnn-svm
A hybrid CNN-SVM architecture for image classification, replacing the softmax classifier with a linear SVM layer.
Not currently ranked — collecting fresh signals.
star history
This repository implements an architecture combining convolutional neural networks (CNN) with linear support vector machines (SVM) for image classification tasks. The project draws inspiration from Y. Tang’s 2013 work on deep learning with SVMs. It replaces the conventional softmax classification layer with a linear SVM while maintaining the CNN feature extraction backbone. The model was evaluated on MNIST and Fashion-MNIST datasets, achieving approximately 99.04% test accuracy on MNIST compared to 99.23% for the CNN-Softmax baseline. Implementation uses TensorFlow.
Frequently asked
- What is AFAgarap/cnn-svm?
- A hybrid CNN-SVM architecture for image classification, replacing the softmax classifier with a linear SVM layer.
- Is cnn-svm open source?
- Yes — AFAgarap/cnn-svm is open source, released under the Apache-2.0 license.
- What language is cnn-svm written in?
- AFAgarap/cnn-svm is primarily written in Python.
- How popular is cnn-svm?
- AFAgarap/cnn-svm has 401 stars on GitHub.
- Where can I find cnn-svm?
- AFAgarap/cnn-svm is on GitHub at https://github.com/AFAgarap/cnn-svm.