tensorflow篇——lamda层

将expand_dim, squeeze或者自定义层转换成keras中的Layer时，一般有两种方法，一种是直接定义类class然后继承Layer，一种是直接使用Lambda函数。
1.lamda层的构建方法如下：

from tensorflow import keras
squeeze = keras.layers.Lambda(lambda x: keras.backend.squeeze(x, axis=-1))(x)
###等同于==========================================================
# squeeze = keras.layers.Lambda(keras.backend.squeeze, arguments={'axis': -1})(x)
###等同于==============================================================
# def squeeze_function(x):
#     return keras.backend.squeeze(x, axis=-1)
# squeeze = keras.layers.Lambda(squeeze_function)(x)

2.通过lamda搭建神经网络：

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Activation, Reshape
from keras.layers import merge
from keras.utils.vis_utils import plot_model
from keras.layers import Input, Lambda
from keras.models import Model

def slice(x, index):
    return x[:, :, index]

a = Input(shape=(4, 2))
x1 = Lambda(slice, output_shape=(4, 1), arguments={'index': 0})(a)
x2 = Lambda(slice, output_shape=(4, 1), arguments={'index': 1})(a)
x1 = Reshape((4, 1, 1))(x1)
x2 = Reshape((4, 1, 1))(x2)
output = merge([x1, x2], mode='concat')
model = Model(a, output)
x_test = np.array([[[1, 2], [2, 3], [3, 4], [4, 5]]])#4*1*2
print(model.predict(x_test))
plot_model(model, to_file='lambda.png', show_shapes=True)

输出：[[[[1. 2.]]

[[2. 3.]]

[[3. 4.]]

[[4. 5.]]]]