Course
Skills Expanded
TensorFlow on Google Cloud
This course covers designing and building a TensorFlow input data pipeline, building ML models with TensorFlow and Keras, improving the accuracy of ML models, writing ML models for scaled use, and writing specialized ML models.
What you'll learn
This course covers designing and building a TensorFlow input data pipeline, building ML models with TensorFlow and Keras, improving the accuracy of ML models, writing ML models for scaled use, and writing specialized ML models.
Table of contents
Introduction to the Course
1min
Introduction to the TensorFlow ecosystem
19mins
Design and Build an Input Data Pipeline
40mins
- Introduction 1m
- An ML recap 3m
- Training on large datasets with tf.data API 4m
- Working in-memory and with files 4m
- Getting the data ready for model training 6m
- Embeddings 9m
- Pluralsight: Getting Started with GCP and Qwiklabs 4m
- Lab intro: TensorFlow Dataset API 0m
- Lab: TensorFlow Dataset API 0m
- Lab intro: Classifying structured data using Keras preprocessing layers 1m
- Lab: Classifying Structured Data using Keras Preprocessing Layers 0m
- Scaling data processing with tf.data and Keras preprocessing layers 10m
- Resources: Design and Build a TensorFlow Input Data Pipeline 0m
Building Neural Networks with the TensorFlow and Keras API
46mins
- Introduction 1m
- Activation functions 9m
- Training neural networks with TensorFlow 2 and the Keras Functional API 10m
- Serving models in the cloud 3m
- Lab intro: Introducing the Keras Sequential API on Vertex AI Platform 1m
- Lab: Introducing the Keras Sequential API on Vertex AI Platform 0m
- Lab intro: Build a DNN using the Keras Functional API on Vertex AI Platform 0m
- Training neural networks with TensorFlow 2 and the Keras Sequential API 8m
- Lab: Build a DNN using the Keras Functional API 0m
- Model subclassing 4m
- (Optional) Lab intro: Making new layers and models via subclassing 1m
- Lab: (Optional) Making New Layers and Models via Subclassing 0m
- Regularization basics 5m
- How can we meaure model complexity: L1 vs. L2 Regularization 5m
- Resources: Building Neural Networks in TensorFlow with Keras API 0m
Training at Scale with Vertex AI
7mins
