This thirteenth video in the Deep learning with Keras series demonstrates how to build and fine-tune a previously trained model to classify whether an image is a cat or a dog. The model used in this video is VGG16, the winner of the 2014 ImageNet competition.
The images used in this video are a random subset of images from the following location: https://www.kaggle.com/c/dogs-vs-cats/data
You will need an account with Kaggle (free) to have the ability to download the data from the link above.
Previous videos in this series:
- Deep learning with Keras - Part 1: Prerequisites for working with Keras
- Deep learning with Keras - Part 2: Configure Keras to use Theano backend (Linux)
- Deep learning with Keras - Part 3: Preprocess training data for Keras model
- Deep learning with Keras - Part 4: Build a single hidden layer model in Keras
- Deep learning with Keras - Part 5: Train a single hidden layer model in Keras
- Deep learning with Keras - Part 6: Create a validation set in Keras
- Deep learning with Keras - Part 7: Make predictions in Keras
- Deep learning with Keras - Part 8: Create confusion matrix for Keras model predictions
- Deep learning with Keras - Part 9: Save and load Keras model
- Deep learning with Keras - Part 10: Set up for CNN training on images in Keras
- Deep learning with Keras - Part 11: Build and train a CNN in Keras
- Deep learning with Keras - Part 12: Predict with a CNN in Keras