基于Theano的深度学习(Deep Learning)框架Keras学习随笔-10-回调

本文介绍了Keras中的回调函数(Callbacks),它允许在模型训练过程中查看内部信息和统计数据。详细讲解了回调函数基类、内置回调如模型检查点(model checkpoints)的使用,以及如何创建自定义回调函数来记录损失率。
摘要由CSDN通过智能技术生成

        原地址:http://blog.csdn.net/niuwei22007/article/details/49229909

        Callbacks(回调函数)是一组用于在模型训练期间指定阶段被调用的函数。可以通过回调函数查看在模型训练过程中的模型内部信息和统计数据。可以通过传递一个回调函数list给fit()函数,然后相关的回调函数就可以在指定的阶段被调用了。

一、Callbacks基类

keras.callbacks.Callback()

属性:

  • Params:字典类型。训练参数(例如verbosity, batch size, numberof epochs…)
  • Model:keras.models.Model类型。被训练模型的引用。

方法:

  • on_train_begin(logs={}):
Implementing deep learning models and neural networks with the power of Python Key FeaturesImplement various deep learning algorithms in Keras and see how deep learning can be used in gamesSee how various deep learning models and practical use cases can be implemented using KerasA practical, hands-on guide with real-world examples to give you a strong foundation in KerasBook Description This book starts by introducing you to supervised learning algorithms such as simple linear regression, the classical multilayer perceptron and more sophisticated deep convolutional networks. You will also explore image processing with recognition of hand written digit images, classification of images into different categories, and advanced objects recognition with related image annotations. An example of identification of salient points for face detection is also provided. Next you will be introduced to Recurrent Networks, which are optimized for processing sequence data such as text, audio or time series. Following that, you will learn about unsupervised learning algorithms such as Autoencoders and the very popular Generative Adversarial Networks (GAN). You will also explore non-traditional uses of neural networks as Style Transfer. Finally, you will look at Reinforcement Learning and its application to AI game playing, another popular direction of research and application of neural networks. What you will learnOptimize step-by-step functions on a large neural network using the Backpropagation AlgorithmFine-tune a neural network to improve the quality of resultsUse deep learning for image and audio processingUse Recursive Neural Tensor Networks (RNTNs) to outperform standard word embedding in special casesIdentify problems for which Recurrent Neural Network (RNN) solutions are suitableExplore the process required to implement AutoencodersEvolve a deep neural network using reinforcement learningWho This Book Is For If you're a data scientist with experience in machine learning or an AI programmer with some exposure to neural networks, you will find this book a useful entry point to deep learning with Keras. A knowledge of Python is required for this book. Table of ContentsNeural Networks FoundationsKeras Installation and APIDeep Learning with ConvNetsGenerative Adversarial Networks and WaveNetWord EmbeddingsRecurrent Neural Networks - RNNsAdditional Deep Learning ModelsAI Game Playing
评论 2
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值