Introduction to TensorFlow 2.0

The release of TensorFlow 2.0 comes with a significant number of improvements over its 1.x version, all with a focus on ease of usability and a better user experience. We will give an overview of what TensorFlow 2.0 is and discuss how to get started building models from scratch using TensorFlow 2.0’s high-level api, Keras. We will walk through an example step-by-step in Python of how to build an image classifier. We will then showcase how to leverage a transfer learning to make building a model even easier! With transfer learning, we can leverage other pretrained models such as ImageNet to drastically speed up the training time of our model. TensorFlow 2.0 makes this incredibly simple to do.

展开查看详情

1.Introduction to TensorFlow 2.0 Brad Miro - @bradmiro Google Spark + AI Summit Europe - October 2019

2.TensorFlow Deep Learning Intro to TensorFlow TensorFlow @ Google 2.0 and Examples Getting Started

3.Deep Learning Doodles courtesy of @dalequark

4.

5.

6.Height Weight

7.Examples of cats Examples of dogs

8.

9.rgb(89,133,204)

10.

11.

12.

13.

14.

15.Use Deep Learning When... You have lots of data (~ 10k+ examples)

16.Use Deep Learning When... You have lots of data (~ 10k+ examples) The problem is “complex” - speech, vision, natural language

17.Use Deep Learning When... You have lots of data (~ 10k+ examples) The problem is “complex” - speech, vision, natural language The data is unstructured

18.Use Deep Learning When... You have lots of data (~ 10k+ examples) The problem is “complex” - speech, vision, natural language The data is unstructured You need the absolute “best” model

19.Don’t Use Deep Learning When... You don’t have a large dataset

20.Don’t Use Deep Learning When... You don’t have a large dataset You are performing sufficiently well with traditional ML methods

21.Don’t Use Deep Learning When... You don’t have a large dataset You are performing sufficiently well with traditional ML methods Your data is structured and you possess the proper domain knowledge

22.Don’t Use Deep Learning When... You don’t have a large dataset You are performing sufficiently well with traditional ML methods Your data is structured and you possess the proper domain knowledge Your model should be explainable

23.

24.TensorFlow Open source deep learning library Utilities to help you write neural networks GPU / TPU support Released by Google in 2015 >2200 Contributors 2.0 released September 2019

25.

26.

27.41,000,000+ 69,000+ 12,000+ 2,200+ downloads commits pull requests contributors

28.TensorFlow @ Google

29.AI-powered data Global localization Portrait Mode on center efficiency in Google Maps Google Pixel