def VGG_16(weights_path=None): model = Sequential() model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))#卷积输入层,指定了输入图像的大小 model.add(Convolution2D(64, 3, 3, activation='relu'))#64个3x3的卷积核,生成64*224*224的图像,激活函数为relu model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(64, 3, 3, activation='relu'))#再来一次卷积 生成64*224*224 model.add(MaxPooling2D((2,2), strides=(2,2)))#pooling操作,相当于变成64*112*112 model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(128, 3, 3, activation='relu')) model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(128, 3, 3, activation='relu')) model.add(MaxPooling2D((2,2), strides=(2,2)))#128*56*56 model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(256, 3, 3, activation='relu')) model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(256, 3, 3, activation='relu')) model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(256, 3, 3, activation='relu')) model.add(MaxPooling2D((2,2), strides=(2,2)))#256*28*28 model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(512, 3, 3, activation='relu')) model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(512, 3, 3, activation='relu')) model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(512, 3, 3, activation='relu')) model.add(MaxPooling2D((2,2), strides=(2,2)))#512*14*14 model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(512, 3, 3, activation='relu')) model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(512, 3, 3, activation='relu')) model.add(ZeroPadding2D((1,1))) model.add(Convolution2D(512, 3, 3, activation='relu')) model.add(MaxPooling2D((2,2), strides=(2,2))) #到这里已经变成了512*7*7 model.add(Flatten())#压平上述向量,变成一维25088 model.add(Dense(4096, activation='relu'))#全连接层有4096个神经核,参数个数就是4096*25088 model.add(Dropout(0.5))#0.5的概率抛弃一些连接 model.add(Dense(4096, activation='relu'))#再来一个全连接 model.add(Dropout(0.5)) model.add(Dense(1000, activation='softmax')) if weights_path: model.load_weights(weights_path) return model
INPUT: [224x224x3] memory: 224*224*3=150K weights: 0 CONV3-64: [224x224x64] memory: 224*224*64=3.2M weights: (3*3*3)*64 = 1,728 CONV3-64: [224x224x64] memory: 224*224*64=3.2M weights: (3*3*64)*64 = 36,864 POOL2: [112x112x64] memory: 112*112*64=800K weights: 0 CONV3-128: [112x112x128] memory: 112*112*128=1.6M weights: (3*3*64)*128 = 73,728 CONV3-128: [112x112x128] memory: 112*112*128=1.6M weights: (3*3*128)*128 = 147,456 POOL2: [56x56x128] memory: 56*56*128=400K weights: 0 CONV3-256: [56x56x256] memory: 56*56*256=800K weights: (3*3*128)*256 = 294,912 CONV3-256: [56x56x256] memory: 56*56*256=800K weights: (3*3*256)*256 = 589,824 CONV3-256: [56x56x256] memory: 56*56*256=800K weights: (3*3*256)*256 = 589,824 POOL2: [28x28x256] memory: 28*28*256=200K weights: 0 CONV3-512: [28x28x512] memory: 28*28*512=400K weights: (3*3*256)*512 = 1,179,648 CONV3-512: [28x28x512] memory: 28*28*512=400K weights: (3*3*512)*512 = 2,359,296 CONV3-512: [28x28x512] memory: 28*28*512=400K weights: (3*3*512)*512 = 2,359,296 POOL2: [14x14x512] memory: 14*14*512=100K weights: 0 CONV3-512: [14x14x512] memory: 14*14*512=100K weights: (3*3*512)*512 = 2,359,296 CONV3-512: [14x14x512] memory: 14*14*512=100K weights: (3*3*512)*512 = 2,359,296 CONV3-512: [14x14x512] memory: 14*14*512=100K weights: (3*3*512)*512 = 2,359,296 POOL2: [7x7x512] memory: 7*7*512=25K weights: 0 FC: [1x1x4096] memory: 4096 weights: 7*7*512*4096 = 102,760,448 FC: [1x1x4096] memory: 4096 weights: 4096*4096 = 16,777,216 FC: [1x1x1000] memory: 1000 weights: 4096*1000 = 4,096,000 TOTAL memory: 24M * 4 bytes ~= 93MB / image (only forward! ~*2 for bwd) TOTAL params: 138M parameters
以上便是整个VGG16的结构图,现在看起来如此的简单