Description
This course will teach you a complete end-to-end workflow for developing deep learning models with Tensorflow, including building, training, evaluating, and predicting models with the Sequential API, validating your models and including regularisation, implementing callbacks, and saving and loading models.
Syllabus :
1. Introduction to TensorFlow
- What's new in TensorFlow
- Interview with Laurence Moroney
- Introduction to Google Colab
- Introduction to Google Colab
- TensorFlow documentation
- TensorFlow installation
- pip installation [Coding tutorial]
- Running TensorFlow with Docker [Coding tutorial]
- Upgrading from TensorFlow
- Upgrading from TensorFlow [Coding tutorial]
2. The Sequential model API
- What is Keras?
- Building a Sequential model
- Building a Sequential model
- Convolutional and pooling layers
- The compile method [Coding tutorial]
- The fit method [Coding tutorial]
- The evaluate and predict methods [Coding tutorial]
3. Validation, regularisation and callbacks
- Interview with Andrew Ng
- Validation sets
- Model regularisation
- Introduction to callbacks
- Early stopping and patience [Coding tutorial]
4. Saving and loading models
- Saving and loading model weights
- Model saving criteria
- Saving the entire model
- Loading pre-trained Keras models
- TensorFlow Hub modules