Vgg16

VGG：

VGG卷积神经网络是牛津大学在2014年提出来的模型。当这个模型被提出时，由于它的简洁性和实用性，马上成为了当时最流行的卷积神经网络模型。它在图像分类和目标检测任务中都表现出非常好的结果。在2014年的ILSVRC比赛中，VGG 在Top-5中取得了92.3%的正确率。 该模型有一些变种，其中最受欢迎的当然是 vgg-16，这是一个拥有16层的模型。你可以看到它需要维度是 224*224*3 的输入数据。

让我们来写一个独立的函数来完整实现这个模型。

from keras.models import Sequential
from keras.layers import Dense,Flatten
from keras.layers import Conv2D
from keras.layers import MaxPooling2D

def generate_vgg16():
    input_shape=(224,224,3)
    model=Sequential([
        Conv2D(64,(3,3),input_shape=input_shape,padding='same',activation='relu'),
        Conv2D(64, (3, 3), padding='same', activation='relu'),
        MaxPooling2D((2, 2), strides=(2, 2)),
        Conv2D(128, (3, 3), activation='relu', padding='same'),
        Conv2D(128, (3, 3), activation='relu', padding='same'),
        MaxPooling2D((2, 2), strides=(2, 2)),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        MaxPooling2D((2, 2), strides=(2, 2)),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        MaxPooling2D((2, 2), strides=(2, 2)),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        Conv2D(256, (3, 3), activation='relu', padding='same'),
        MaxPooling2D((2, 2), strides=(2, 2)),
        Flatten(),
        Dense(4096, activation='relu'),
        Dense(4096, activation='relu'),
        Dense(1000, activation='softmax')
    ])
    return model


if __name__ == '__main__':
    model=generate_vgg16()
    model.summary()

运行结果：

Model: "sequential_1"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 224, 224, 64)      1792      
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 224, 224, 64)      36928     
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 112, 112, 64)      0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 112, 112, 128)     73856     
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 112, 112, 128)     147584    
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 56, 56, 128)       0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 56, 56, 256)       295168    
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 56, 56, 256)       590080    
_________________________________________________________________
conv2d_7 (Conv2D)            (None, 56, 56, 256)       590080    
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 28, 28, 256)       0         
_________________________________________________________________
conv2d_8 (Conv2D)            (None, 28, 28, 256)       590080    
_________________________________________________________________
conv2d_9 (Conv2D)            (None, 28, 28, 256)       590080    
_________________________________________________________________
conv2d_10 (Conv2D)           (None, 28, 28, 256)       590080    
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 14, 14, 256)       0         
_________________________________________________________________
conv2d_11 (Conv2D)           (None, 14, 14, 256)       590080    
_________________________________________________________________
conv2d_12 (Conv2D)           (None, 14, 14, 256)       590080    
_________________________________________________________________
conv2d_13 (Conv2D)           (None, 14, 14, 256)       590080    
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 7, 7, 256)         0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 12544)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 4096)              51384320  
_________________________________________________________________
dense_2 (Dense)              (None, 4096)              16781312  
_________________________________________________________________
dense_3 (Dense)              (None, 1000)              4097000   
=================================================================
Total params: 77,538,600
Trainable params: 77,538,600
Non-trainable params: 0
_________________________________________________________________