tensorflow2 常用api使用

2022-06-10 04:22:26

1、embedding层

　　作用是将正整数（下标）转换为具有固定大小的向量，如[[4],[20]]->[[0.25,0.1],[0.6,-0.2]]

1.1 api

　　tf.keras.layers.Embedding

tf.keras.layers.Embedding(
    input_dim, output_dim, embeddings_initializer=‘uniform‘,
    embeddings_regularizer=None, activity_regularizer=None,
    embeddings_constraint=None, mask_zero=False, input_length=None, **kwargs
)

Arguments
`input_dim`	Integer. Size of the vocabulary, i.e. maximum integer index + 1. 词汇表的长度，输入数据最大下标+1
`output_dim`	Integer. Dimension of the dense embedding. 全连接嵌入的维度，即1个正整数转化为的向量的长度
`embeddings_initializer`	Initializer for the `embeddings` matrix (see `keras.initializers`).
`embeddings_regularizer`	Regularizer function applied to the `embeddings` matrix (see `keras.regularizers`).
`embeddings_constraint`	Constraint function applied to the `embeddings` matrix (see `keras.constraints`).
`mask_zero`	Boolean, whether or not the input value 0 is a special "padding" value that should be masked out. This is useful when using recurrent layers which may take variable length input. If this is `True`, then all subsequent layers in 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 be used in the vocabulary (input_dim should equal size of vocabulary + 1). 布尔值，确定是否将输入中的‘0’看作是应该被忽略的‘填充’（padding）值，该参数在使用递归层处理变长输入时有用。设置为True的话，模型中后续的层必须都支持masking，否则会抛出异常。如果该值为True，则下标0在字典中不可用，input_dim应设置为\|vocabulary\| + 1。
`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). 当输入序列的长度固定时，该值为其长度。如果要在该层后接Flatten层，然后接Dense层，则必须指定该参数，否则Dense层的输出维度无法自动推断。

1.2 实例

import tensorflow as tf
import numpy as np 

model = tf.keras.Sequential()
model.add(tf.keras.layers.Embedding(65, 64, input_length=10))
# The model will take as input an integer matrix of size (batch,
# input_length), and the largest integer (i.e. word index) in the input
# should be no larger than 999 (vocabulary size).
# Now model.output_shape is (None, 10, 64), where `None` is the batch
# dimension.
input_array = np.random.randint(65, size=(32, 10))
print(input_array.shape)
model.compile(‘rmsprop‘, ‘mse‘)
output_array = model.predict(input_array)
print(output_array.shape)
#(32, 10)
#(32, 10, 64)
# 65为所有词汇的大小，所以下面randint取值也是要在0-65范围内取值；如果randint取值大于65的话，会报错
# Embedding参数input_length为输入的每条数据的维度，randint可以看出(32, 10)，batch_size为32， 每条数据长度为10
# Embedding第二个参数64表示输出数据的维度，即每条数据的维度的每一个值会变成长度为64的向量

输入输出数据变换：输入数据形状为（32， 10），其中32位batch_size, 10位每个数据的维度；Embedding层设置输入数据维度为10（和输入数据符合），输出数据维度为64，即每条数据的维度的每一个值会变成长度为64的向量；所以输出数据形状为（32,10,64）

2.Conv1d

　　tf.keras.layers.Conv1D

2.1 api

Arguments
`filters`	Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution). 卷积核个数
`kernel_size`	An integer or tuple/list of a single integer, specifying the length of the 1D convolution window. 卷积核大小，卷积核其实应该是一个二维的，这里只需要指定一维，是因为卷积核的第二维与输入的词向量维度是一致的，因为对于句子而言，卷积的移动方向只能是沿着词的方向，即只能在列维度移动
`strides`	An integer or tuple/list of a single integer, specifying the stride length of the convolution. Specifying any stride value != 1 is incompatible with specifying any `dilation_rate` value != 1. 步长
`padding`	One of `"valid"`, `"same"` or `"causal"` (case-insensitive). `"valid"` means no padding. `"same"` results in padding evenly to the left/right or up/down of the input such that output has the same height/width dimension as the input. `"causal"` results in causal (dilated) convolutions, e.g. `output[t]` does not depend on `input[t+1:]`. Useful when modeling temporal data where the model should not violate the temporal order. See WaveNet: A Generative Model for Raw Audio, section 2.1.
`data_format`	A string, one of `channels_last` (default) or `channels_first`.
`dilation_rate`	an integer or tuple/list of a single integer, specifying the dilation rate to use for dilated convolution. Currently, specifying any `dilation_rate` value != 1 is incompatible with specifying any `strides` value != 1.
`groups`	A positive integer specifying the number of groups in which the input is split along the channel axis. Each group is convolved separately with `filters / groups` filters. The output is the concatenation of all the `groups` results along the channel axis. Input channels and `filters` must both be divisible by `groups`.
`activation`	Activation function to use. If you don‘t specify anything, no activation is applied ( see `keras.activations`). 激活函数
`use_bias`	Boolean, whether the layer uses a bias vector.
`kernel_initializer`	Initializer for the `kernel` weights matrix ( see `keras.initializers`).
`bias_initializer`	Initializer for the bias vector ( see `keras.initializers`).
`kernel_regularizer`	Regularizer function applied to the `kernel` weights matrix (see `keras.regularizers`).
`bias_regularizer`	Regularizer function applied to the bias vector ( see `keras.regularizers`).
`activity_regularizer`	Regularizer function applied to the output of the layer (its "activation") ( see `keras.regularizers`). 正则项
`kernel_constraint`	Constraint function applied to the kernel matrix ( see `keras.constraints`).
`bias_constraint`	Constraint function applied to the bias vector ( see `keras.constraints`).

2.2 实例

# The inputs are 128-length vectors with 10 timesteps, and the batch size
# is 4.
input_shape = (4, 10, 128)
x = tf.random.normal(input_shape)
y = tf.keras.layers.Conv1D(32, 3, activation=‘relu‘,input_shape=input_shape[1:])(x)
print(y.shape)
#(4, 8, 32)

1维卷积经常用于处理文本，上面实例以文本角度解释。

输入文本形状为（4, 10, 128），batch_size为4，句子长度为10，句子的每个单词用128的向量表示。Conv1D第一个参数表示卷积核个数为32，卷积核长度为3*128（见上面参数解释）；所以对应输出形状为（4 ，（10-3+1）， 32（卷积核个数））= （4， 8，32）