weixin_36670529的博客

Class InitializerInitializer base class: all initializers inherit from this class.Aliases:Class tf.compat.v2.initializers.Initializer Class tf.compat.v2.keras.initializers.Initializer Class tf...

to_categorical(y, num_classes=None, dtype='float32')将整型标签转为onehot。y为int数组，num_classes为标签类别总数，大于max(y)（标签从0开始的）。返回：如果num_classes=None，返回len(y) * [max(y)+1]（维度，m*n表示m行n列矩阵，下同），否则为len(y) * num_classe...

Keras backend API.一、Functionsabs(...): Element-wise absolute value. all(...): Bitwise reduction (logical AND). any(...): Bitwise reduction (logical OR). arange(...): Creates a 1D tensor contain...

Keras Applications are canned architectures with pre-trained weights.Modulesdensenet module: DenseNet models for Keras. imagenet_utils module: Utilities for ImageNet data preprocessing & pred...

Callbacks: utilities called at certain points during model training.Classesclass BaseLogger: Callback that accumulates epoch averages of metrics. class CSVLogger: Callback that streams epoch resu...

Built-in optimizer classes.Modulesschedules module: Public API for tf.keras.optimizers.schedules namespace.Classesclass Adadelta: Optimizer that implements the Adadelta algorithm. class Adagra...

Keras utilities.Classesclass CustomObjectScope: Provides a scope that changes to _GLOBAL_CUSTOM_OBJECTS cannot escape. class GeneratorEnqueuer: Builds a queue out of a data generator. class HDF5...

Set of tools for real-time data augmentation on image data.Classesclass DirectoryIterator: Iterator capable of reading images from a directory on disk. class ImageDataGenerator: Generate batches ...

Keras backend API.Functionsabs(...): Element-wise absolute value. all(...): Bitwise reduction (logical AND). any(...): Bitwise reduction (logical OR). arange(...): Creates a 1D tensor containin...

Modulesboston_housing module: Boston housing price regression dataset. cifar10 module: CIFAR10 small images classification dataset. cifar100 module: CIFAR100 small images classification dataset. ...

Keras是目前使用最为广泛的深度学习工具之一，它的底层可以支持TensorFlow、MXNet、CNTK和Theano。如今，Keras更是被直接引入了TensorFlow的核心代码库，成为TensorFlow官网提供的高层封装之一。下面首先介绍最基本的Keras API，下面给出一个简单的样例，然后介绍如何使用Keras定义更加复杂的模型以及如何将Keras和原生态TensorFlow结合起来...

目录Class ModelUsed in the guide:Used in the tutorials:__init__Propertieslayersmetrics_namesrun_eagerlysample_weightsstate_updatesstatefulMethodscompileevaluateevaluate_gen...

目录Class SequentialUsed in the guide:Used in the tutorials: __init__Propertieslayersmetrics_namesrun_eagerlysample_weightsstate_updatesstatefulMethodsaddcompileeva...

Keras layers API.Aliases:Module tf.compat.v1.keras.layersClassesclass AbstractRNNCell: Abstract object representing an RNN cell. class Activation: Applies an activation function to an output....