摘要：網絡結構來自固定隨機數種子以復現結果創建維向量，并擴展維度適應對輸入的要求，的大小為定義卷積層卷積核數量為卷積核大小為定義最大化池化層平鋪層，調整維度適應全鏈接層定義全鏈接層編譯模型打印層的輸出打印網絡結構最終輸出如下卷積結果網絡結

網絡結構來自https://github.com/nfmcclure/...

import numpy as np
import keras

# 固定隨機數種子以復現結果
seed=13
np.random.seed(seed)

# 創建 1 維向量，并擴展維度適應 Keras 對輸入的要求， data_1d 的大小為 (1, 25, 1)
data_1d = np.random.normal(size=25)
data_1d = np.expand_dims(data_1d, 0)
data_1d = np.expand_dims(data_1d, 2)

# 定義卷積層
filters = 1 # 卷積核數量為 1
kernel_size = 5 # 卷積核大小為 5
convolution_1d_layer = keras.layers.convolutional.Conv1D(filters, kernel_size, strides=1, padding="valid", input_shape=(25, 1), activation="relu", name="convolution_1d_layer")

# 定義最大化池化層
max_pooling_layer = keras.layers.MaxPool1D(pool_size=5, strides=1, padding="valid", name="max_pooling_layer")

# 平鋪層，調整維度適應全鏈接層
reshape_layer = keras.layers.core.Flatten(name="reshape_layer")

# 定義全鏈接層
full_connect_layer = keras.layers.Dense(5, kernel_initializer=keras.initializers.RandomNormal(mean=0.0, stddev=0.1, seed=seed), bias_initializer="random_normal", use_bias=True, name="full_connect_layer")

# 編譯模型
model = keras.Sequential()
model.add(convolution_1d_layer)
model.add(max_pooling_layer)
model.add(reshape_layer)
model.add(full_connect_layer)

# 打印 full_connect_layer 層的輸出
output = keras.Model(inputs=model.input, outputs=model.get_layer("full_connect_layer").output).predict(data_1d)
print(output)

# 打印網絡結構
print(model.summary())

最終輸出如下

======================卷積結果=========================
[[-0.0131043  -0.11734447  0.13395447 -0.75453871 -0.69782442]]
======================網絡結構=========================
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
convolution_1d_layer (Conv1D (None, 21, 1)             6         
_________________________________________________________________
max_pooling_layer (MaxPoolin (None, 17, 1)             0         
_________________________________________________________________
reshape_layer (Flatten)      (None, 17)                0         
_________________________________________________________________
full_connect_layer (Dense)   (None, 5)                 90        
=================================================================
Total params: 96
Trainable params: 96
Non-trainable params: 0
_________________________________________________________________
None

data_size = [10, 10]
data_2d = np.random.normal(size=data_size)
data_2d = np.expand_dims(data_2d, 0)
data_2d = np.expand_dims(data_2d, 3)
print data_2d.shape

# 定義卷積層
conv_size = 2
conv_stride_size = 2
convolution_2d_layer = keras.layers.Conv2D(filters=1, kernel_size=(conv_size, conv_size), strides=(conv_stride_size, conv_stride_size), input_shape=(data_size[0], data_size[0], 1))
# convolution_2d_layer = keras.layers.Conv2D(filter=1, kernel_size=kernel, strides=[1,1], padding="valid", activation="relu", name="convolution_2d_layer", input_shape=(1, data_size[0], data_size[0]))


# 定義最大化池化層
pooling_size = (2, 2)
max_pooling_2d_layer = keras.layers.MaxPool2D(pool_size=pooling_size, strides=1, padding="valid", name="max_pooling_2d_layer")

# 平鋪層，調整維度適應全鏈接層
reshape_layer = keras.layers.core.Flatten(name="reshape_layer")

# 定義全鏈接層
full_connect_layer = keras.layers.Dense(5, kernel_initializer=keras.initializers.RandomNormal(mean=0.0, stddev=0.1, seed=seed), bias_initializer="random_normal", use_bias=True, name="full_connect_layer")

model_2d = keras.Sequential()
model_2d.add(convolution_2d_layer)
model_2d.add(max_pooling_2d_layer)
model_2d.add(reshape_layer)
model_2d.add(full_connect_layer)

# 打印 full_connect_layer 層的輸出
output = keras.Model(inputs=model_2d.input, outputs=model_2d.get_layer("full_connect_layer").output).predict(data_2d)
print("======================卷積結果=========================")
print(output)

# 打印網絡結構
print("======================網絡結構=========================")
print(model_2d.summary())

輸出

======================卷積結果=========================
[[ 0.30173036 -0.10435719 -0.03354734  0.24000235 -0.09962128]]
======================網絡結構=========================
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 5, 5, 1)           5         
_________________________________________________________________
max_pooling_2d_layer (MaxPoo (None, 4, 4, 1)           0         
_________________________________________________________________
reshape_layer (Flatten)      (None, 16)                0         
_________________________________________________________________
full_connect_layer (Dense)   (None, 5)                 85        
=================================================================
Total params: 90
Trainable params: 90
Non-trainable params: 0
_________________________________________________________________
None