Skip to content
#

cnn-classification

Here are 2,092 public repositories matching this topic...

Algorithm that identifies the dog's breed given an image of a dog, or the resembling dog breed of a human face. Uses a Haar feature-based cascade classifier to detect humans, a pre-trained ResNet-50 model to detect dogs, and a fine-tuned Xception model for dog breed classification. Achieves a test accuracy of around 85% on a test set of 800 images.

  • Updated Nov 10, 2017
  • Jupyter Notebook

Improve this page

Add a description, image, and links to the cnn-classification topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the cnn-classification topic, visit your repo's landing page and select "manage topics."

Learn more