Tensorflow 2.0 学习资料_progressive disclosure of complexity-优快云博客

本文链接：https://blog.youkuaiyun.com/CrazyTensor/article/details/102292065

这篇博客汇总了TensorFlow 2.0的学习资源，包括官方教程、Keras crash course以及深入视频讲解。此外，还介绍了TensorFlow 2.0中的Keras API，强调其易用性和逐步增加复杂性的特性。同时，提到了TensorBoard等库和扩展，以及Keras Functional API的优势。文章还涵盖了训练和评估模型、自定义层、损失函数、指标和模型保存等内容。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

https://www.tensorflow.org/tutorials/text/word_embeddings
https://www.tensorflow.org/tutorials/text/nmt_with_attention
https://www.tensorflow.org/tutorials/text/transformer
https://www.tensorflow.org/tutorials/text/image_captioning

A machine learning platform from the future.
A core principle of Keras is “progressive disclosure of complexity”: it’s easy to get started, and you can gradually dive into workflows where you write more and more logic from scratch, providing you with complete control. This applies to both model definition, and model training. Model definition: spectrum of workflows Model training: spectrum of workflows

Resources to learn TensorFlow 2.0

TensorFlow 2.0 + Keras Crash Course by Francois Chollet
- differences between models defined via subclassing and Functional models
The Keras functional API in TensorFlow from official guide
Train and evaluate with TensorFlow 2.0 from official guide
Hands-On Machine Learning with Scikit-Learn, Keras and Tensor Flow by Aurélien Géron
Inside TensorFlow: tf.Keras (video part 1) by Francois Chollet
Inside TensorFlow: tf.Keras (video part 2) by Francois Chollet

Libraries and extensions

Tensorboard：https://www.tensorflow.org/tensorboard

部分笔记：

@tf.function: compile the training function into a static graph to speedup over 40%.

custom layers：

class Linear(Layer):
  """y = w.x + b"""

  # 定义全局变量
  def __init__(self, units=32