Keras 實現AlexNet

from keras.models import Sequential
from keras.layers import Dense, Flatten, Dropout
from keras.layers.convolutional import Conv2D, MaxPooling2D
from keras.utils.np_utils import to_categorical
import numpy as np
seed = 7
np.random.seed(seed)

# 創建模型序列
model = Sequential()
#第一層卷積網絡，使用96個卷積核，大小爲11x11步長爲4， 要求輸入的圖片爲227x227， 3個通道，不加邊，激活函數使用relu
model.add(Conv2D(96, (11, 11), strides=(1, 1), input_shape=(28, 28, 1), padding='same', activation='relu',
                 kernel_initializer='uniform'))
# 池化層
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
# 第二層加邊使用256個5x5的卷積核，加邊，激活函數爲relu
model.add(Conv2D(256, (5, 5), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
#使用池化層，步長爲2
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))
# 第三層卷積，大小爲3x3的卷積核使用384個
model.add(Conv2D(384, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
# 第四層卷積,同第三層
model.add(Conv2D(384, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
# 第五層卷積使用的卷積核爲256個，其他同上
model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
model.add(MaxPooling2D(pool_size=(3, 3), strides=(2, 2)))

model.add(Flatten())
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
model.summary()