This project from the Udacity Deep Learning Nanodegree Programme deploys the use of Convolutional Neural Networks (CNN) in PyTorch to classify dog breeds.
- PyTorch
- Convolutional Neural Networks (CNN)
- Data augmentation
- OpenCV pre-trained face detectors (haarcascades & lbpcascade)
- Pre-trained VGG-16 convolutional network
- Transfer Learning
Open dog_app.ipynb
on a jupyter notebook environment, or Google colab. The notebook consists of further technical details.
Deploys the CNN dog classifier model as a flask or django web application