Duration
21 hours (usually 3 days including breaks)
Requirements
- Python Programming experience.
- Experience with the Linux command line.
Audience
- Developers
- Data scientists
Overview
Keras is a high-level neural networks API for fast development and experimentation. It runs on top of TensorFlow, CNTK, or Theano.
This instructor-led, live training (online or onsite) is aimed at technical persons who wish to apply deep learning model to image recognition applications.
By the end of this training, participants will be able to:
- Install and configure Keras.
- Quickly prototype deep learning models.
- Implement a convolutional network.
- Implement a recurrent network.
- Execute a deep learning model on both a CPU and GPU.
Format of the Course
- Interactive lecture and discussion.
- Lots of exercises and practice.
- Hands-on implementation in a live-lab environment.
Course Customization Options
- To request a customized training for this course, please contact us to arrange.
- To learn more about Keras, please visit: https://keras.io/
Course Outline
Introduction
Overview of Neural Networks
Understanding Convolutional Networks
Setting up Keras
Overview of Keras Features and Architecture
Overview of Keras Syntax
Understanding How a Keras Model Organize Layers
Configuring the Keras Backend (TensorFlow or Theano)
Implementing an Unsupervised Learning Model
Analyzing Images with a Convolutional Neural Network (CNN)
Preprocessing Data
Training the Model
Training on CPU vs GPU vs TPU
Evaluating the Model
Using a Pre-trained Deep Learning Model
Setting up a Recurrent Neural Network (RNN)
Debugging the Model
Saving the Model
Deploying the Model
Monitoring a Keras Model with TensorBoard
Troubleshooting
Summary and Conclusion