border_mode

如果border_mode选择为same,那么卷积操作的输入和输出尺寸会保持一致。如果选择valid,那卷积过后,尺寸会变小

# apply a 3x3 convolution with 64 output filters on a 256x256 image:
model = Sequential()
model.add(Convolution2D(64, 3, 3, border_mode='same', input_shape=(3, 256, 256)))
# now model.output_shape == (None, 64, 256, 256)

>> definition in keras:
def conv_output_length(input_length, filter_size, border_mode, stride):  
    if input_length is None:  
        return None  
    assert border_mode in {'same', 'valid'}  
    if border_mode == 'same':  
        output_length = input_length  
    elif border_mode == 'valid':  
        output_length = input_length - filter_size + 1  
    return (output_length + stride - 1) // stride