Share Description
In this course, you will learn how to use TensorFlow to create fully customised deep learning models and workflows for any application. TensorFlow's lower level APIs will be used to create complex model architectures, fully customised layers, and a flexible data workflow. You will also broaden your understanding of TensorFlow APIs to include sequence models.
Syllabus :
1. The Keras functional API
- The Keras functional API
- Multiple inputs and outputs
- Variables
- Tensors
- Variables and Tensors
- Accessing layer Variables
- Accessing layer Tensors
- Freezing layers
2. Data Pipeline
- Keras datasets
- Dataset generators
- Keras image data augmentation
- The Dataset class
- Training with Datasets
3. Sequence Modelling
- Preprocessing sequence data
- The IMDB dataset
- Padding and masking sequence data
- The Embedding layer
- The Embedding Projector
- Recurrent neural network layers
- Stacked RNNs and the Bidirectional wrapper
4. Model subclassing and custom training loops
- Model subclassing
- Custom layers
- Automatic differentiation
- Custom training loops
- tf.function decorator
