如何网站做百度推广爱站seo工具包

keras目录文件详解5.1（embeddings.py）-keras学习笔记五

keras\layers\embeddings.py

建立词向量嵌入层，把输入文本转为可以进一步处理的数据格式（例如，矩阵）

Keras开发包文件目录

Keras实例文件目录

代码注释

"""Embedding layer.
# 嵌入层
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_functionfrom .. import backend as K
from .. import initializers
from .. import regularizers
from .. import constraints
from ..engine import Layer
from ..legacy import interfacesclass Embedding(Layer):"""Turns positive integers (indexes) into dense vectors of fixed size.将正整数（索引）转换成固定大小的全连接向量。eg. [[4], [20]] -> [[0.25, 0.1], [0.6, -0.2]]This layer can only be used as the first layer in a model.本层只能用作模型第一层# Example举例：```pythonmodel = Sequential()model.add(Embedding(1000, 64, input_length=10))# the model will take as input an integer matrix of size (batch, input_length).该模型将作为输入的整数矩阵的大小（batch, input_length）。## the largest integer (i.e. word index) in the input should be no larger than 999 (vocabulary size).输入中最大的整数（即单词索引）不应大于999（vocabulary size,词汇量）。# now model.output_shape == (None, 10, 64), where None is the batch dimension.现在模型输出形状.output_shape == (None, 10, 64),None是批次的维度input_array = np.random.randint(1000, size=(32, 10))model.compile('rmsprop', 'mse')output_array = model.predict(input_array)assert output_array.shape == (32, 10, 64)```# Argumentsinput_dim: int > 0. Size of the vocabulary,input_dim: int > 0. 词汇总数（大小，量）i.e. maximum integer index + 1.output_dim: int >= 0. Dimension of the dense embedding.output_dim: int >= 0. 全连接嵌入的维度.embeddings_initializer: Initializer for the `embeddings` matrixembeddings_initializer: 嵌入矩阵初始化(see [initializers](../initializers.md)).(见 [initializers](../initializers.md)).embeddings_regularizer: Regularizer function applied tothe `embeddings` matrix(see [regularizer](../regularizers.md)).embeddings_regularizer: 嵌入矩阵的规则化函数(见 [regularizer](../regularizers.md)).embeddings_constraint: Constraint function applied tothe `embeddings` matrix约束函数在“嵌入”矩阵中的应用(see [constraints](../constraints.md)).(见 [constraints](../constraints.md)).mask_zero: Whether or not the input value 0 is a special "padding"value that should be masked out.输入值0是否是一个特殊的“填充”值，应该被屏蔽掉。This is useful when using [recurrent layers](recurrent.md)使用 [recurrent layers](recurrent.md)是有用的which may take variable length input.可以采用可变长度的输入。If this is `True` then all subsequent layersin the model need to support masking or an exception will be raised.If mask_zero is set to True, as a consequence, index 0 cannot beused in the vocabulary (input_dim should equal size ofvocabulary + 1).如果这是“真”，那么模型中的所有后续层都需要支持掩蔽，否则将引发异常。如果mask_zero设置为true，因此，索引0不能在词汇表中使用（input_dim应该等于vocabulary + 1的大小）。input_length: Length of input sequences, when it is constant.This argument is required if you are going to connect`Flatten` then `Dense` layers upstream(without it, the shape of the dense outputs cannot be computed).input_length: 输入序列的长度，当它是常数时。如果要连接上游的“Flatten”和“Dense”层（如果没有它，则无法计算全连接输出的形状），则需要此参数。# Input shape输入形状2D tensor with shape: `(batch_size, sequence_length)`.2维张量，形状：(batch_size, sequence_length)`.# Output shape输出形状3D tensor with shape: `(batch_size, sequence_length, output_dim)`.3维张量，形状: `(batch_size, sequence_length, output_dim)`.# References参考- [A Theoretically Grounded Application of Dropout in Recurrent Neural Networks](http://arxiv.org/abs/1512.05287)- [循环（递归）神经网络中Dropout理论的一个接地应用](http://arxiv.org/abs/1512.05287)"""@interfaces.legacy_embedding_supportdef __init__(self, input_dim, output_dim,embeddings_initializer='uniform',embeddings_regularizer=None,activity_regularizer=None,embeddings_constraint=None,mask_zero=False,input_length=None,**kwargs):if 'input_shape' not in kwargs:if input_length:kwargs['input_shape'] = (input_length,)else:kwargs['input_shape'] = (None,)super(Embedding, self).__init__(**kwargs)self.input_dim = input_dimself.output_dim = output_dimself.embeddings_initializer = initializers.get(embeddings_initializer)self.embeddings_regularizer = regularizers.get(embeddings_regularizer)self.activity_regularizer = regularizers.get(activity_regularizer)self.embeddings_constraint = constraints.get(embeddings_constraint)self.mask_zero = mask_zeroself.input_length = input_lengthdef build(self, input_shape):self.embeddings = self.add_weight(shape=(self.input_dim, self.output_dim),initializer=self.embeddings_initializer,name='embeddings',regularizer=self.embeddings_regularizer,constraint=self.embeddings_constraint,dtype=self.dtype)self.built = Truedef compute_mask(self, inputs, mask=None):if not self.mask_zero:return Noneelse:return K.not_equal(inputs, 0)def compute_output_shape(self, input_shape):if self.input_length is None:return input_shape + (self.output_dim,)else:# input_length can be tuple if input is 3D or higher# 如果输入是3维或更高（维度），输入长度可以是元组。if isinstance(self.input_length, (list, tuple)):in_lens = list(self.input_length)else:in_lens = [self.input_length]if len(in_lens) != len(input_shape) - 1:ValueError('"input_length" is %s, but received input has shape %s' %(str(self.input_length), str(input_shape)))else:for i, (s1, s2) in enumerate(zip(in_lens, input_shape[1:])):if s1 is not None and s2 is not None and s1 != s2:ValueError('"input_length" is %s, but received input has shape %s' %(str(self.input_length), str(input_shape)))elif s1 is None:in_lens[i] = s2return (input_shape[0],) + tuple(in_lens) + (self.output_dim,)def call(self, inputs):if K.dtype(inputs) != 'int32':inputs = K.cast(inputs, 'int32')out = K.gather(self.embeddings, inputs)return outdef get_config(self):config = {'input_dim': self.input_dim,'output_dim': self.output_dim,'embeddings_initializer': initializers.serialize(self.embeddings_initializer),'embeddings_regularizer': regularizers.serialize(self.embeddings_regularizer),'activity_regularizer': regularizers.serialize(self.activity_regularizer),'embeddings_constraint': constraints.serialize(self.embeddings_constraint),'mask_zero': self.mask_zero,'input_length': self.input_length}base_config = super(Embedding, self).get_config()return dict(list(base_config.items()) + list(config.items()))

代码执行

Keras详细介绍

英文：https://keras.io/

中文：http://keras-cn.readthedocs.io/en/latest/

实例下载

https://github.com/keras-team/keras

https://github.com/keras-team/keras/tree/master/examples

完整项目下载

方便没积分童鞋，请加企鹅452205574，共享文件夹。

包括：代码、数据集合（图片）、已生成model、安装库文件等。