Skip to main content

Table 1 VGGNet model

From: Mural classification model based on high- and low-level vision fusion

Layer Size Filter Stride Dropout
Input 224 × 224 × 3    
Conv1 224 × 224 × 64 3 × 3 × 64 × 2 1  
MaxPool1 112 × 112 × 64 2 × 2 2  
Conv2 112 × 112 × 128 3 × 3 × 128 × 2 1  
MaxPool2 56 × 56 × 128 2 × 2 2  
Conv3 56 × 56 × 256 3 × 3 × 256 × 3 1  
MaxPool3 28 × 28 × 256 2 × 2 2  
Conv4 28 × 28 × 512 3 × 3 × 512 × 3 1  
MaxPool4 14 × 14 × 512 2 × 2 2  
Conv5 14 × 14 × 512 3 × 3 × 512 × 3 1  
MaxPool5 7 × 7 × 512 2 × 2 2  
Fc6 4096    0.5
Fc7 4096    0.5
Softmax 1000