Google Software Engineer Matthew Watson highlights Keras Preprocessing Layers’ ability to streamline model development workflows. Follow along as he builds an end-to-end model showing what you can do with these layers.
Chapters
0:00 - Introduction
1:18 - Identifying the problem
6:01 - What are Keras preprocessing layers
9:45 - Preprocessing layers that are offered
17:37 - Transforming inputs from strings to a numeric input
22:17 - Building a simple model
24:13 - Adding a new feature
27:40 - Better performance with tf.data
33:22 - Multi worker training
35:26 - Takeaways
Resources:
Matthew Watson Github → https://goo.gle/3wfFjGY
Preprocessing layers guide → https://goo.gle/36qE2SA
Text loading tutorial → https://goo.gle/3JyFCR2
Image loading tutorial → https://goo.gle/3IuJZew
Watch more ML Tech Talks → https://goo.gle/ml-tech-talks
Subscribe to TensorFlow → https://goo.gle/TensorFlow
product: TensorFlow - General;