Get started with TensorFlow's High-Level APIs (With TimeLine)


Introduction to Tensor Flow using both Jupyter Noteooks and PyCharm. TimeLine included at the bottom so that you can skip to the part that interests you.

Upvotes: DownVotes:
Age: a year     Page Views: 184190
Votes / View: 12    Wilson Score: 0.98

High-level APIs like tf.keras enable developers to train models easily and effectively. This session will introduce these APIs, and notebooks you can run live in the browser to get started using Colab. 

We'll walk you through writing your first neural network in TensorFlow using just 10 lines of code with tf.keras, and then we’ll introduce you to Eager execution. We'll close with educational resources you can use to learn more about ML. By releasing easier and more intuitive APIs, we hope to make TensorFlow, an open-source machine learning framework more accessible for all. Rate this session by signing-in on the I/O website here → Try TensorFlow with zero install → Train your first neural network with just 10 lines of code → Use the same Keras-compatible API with TensorFlow.js! → Learn more about ML →


0:00 Introductions

3:05 The Notebook URLs

3:50 Several Notebooks

5:44 Designing Experiments

6:50 Making TensorFlow Easy to Use.

7:04 TensorFlow.js

7:38 Magenta

8:05 Cell Bot (Biology Project)

8:50 Colab

9:15 Jupyter Notebooks.

10:55 Your First Neural Network (Keras)

13: Format of NMIST Data

14:10 Build the model

15:30 Memorizing Data Vs Pattern Recognition

16:35 Compile + Loss Functions

17:45 Explaining Gradient Descent

19:18  Epochs

20:03 Like Tuning a guitar

21:23 Evaluate and Predict

22:38 Start Simple


24:39 Eager Execution


25:52 Second Speaker (TensorFlow with PyCharm)

28:27 Cats or Dogs

29:50 ML is very different

31:05 Debugging with PyCharm and Eager Mode

36:40 Recommended Resources

37:50 TensorFlow.js

38:15 Links