Building Machine Learning Solutions with TensorFlow 2.0 (Path)

谷歌于 2019 年 10 月发布了 TensorFlow 2.0，它使用动态图并且对 Python 更加友好。有多项更改可确保删除冗余 API 并更好地与 Python 运行时和 Eager Execution 集成。

• 了解开始使用Tensorflow 2.0 所需的一切。
• 通过学习如何为 TensorFlow 2.0 设计数据管道和实施超参数调整来加深对 TensorFlow 的理解。
• 了解如何使用 Keras 构建机器学习工作流程并使用时间序列数据生成高性能预测和预测。

此路径中的课程

A1。TensorFlow 2.0 入门（Janani Ravi，2020）
B1。使用 TensorFlow 2.0 设计数据管道（Chase DeHan，2020）
B3。使用 TensorFlow.js 构建机器学习解决方案（Abhishek Kumar，2020）
C1。
使用 Keras TensorFlow 2.0 (Janani Ravi, 2020) C2构建机器学习工作流。使用 TensorFlow 2.0 实施时间序列分析、预测和预测（Chase DeHan，2020 年）

Google released TensorFlow 2.0 in October 2019 which uses the dynamic graph and is more Python friendly. There are multiple changes to ensure removal of redundant APIs and better integration with Python runtime and Eager Execution.

• Learn everything you need to know to get started with Tensorflow 2.0.
• Step up your TensorFlow understanding by learning how to design data pipelines and implement hyperparameter tuning for Tensorflow 2.0.
• Learn how to build a machine learning workflow with Keras and work with time series data to generate high performing forecasts and predictions.

Courses in this path

A1. Getting Started with TensorFlow 2.0 (Janani Ravi, 2020)
B1. Designing Data Pipelines with TensorFlow 2.0 (Chase DeHan, 2020)
B3. Building Machine Learning Solutions with TensorFlow.js (Abhishek Kumar, 2020)
C1. Build a Machine Learning Workflow with Keras TensorFlow 2.0 (Janani Ravi, 2020)
C2. Implement Time Series Analysis, Forecasting and Prediction with TensorFlow 2.0 (Chase DeHan, 2020)