我试图理解 Keras 中的 model.summary()
。我有以下卷积神经网络。第一个卷积的值是:
conv2d_4 (Conv2D) (None, 148, 148, 16) 448
148和448从何而来?
代码
image_input = layers.Input(shape=(150, 150, 3))
x = layers.Conv2D(16, 3, activation='relu')(image_input)
x = layers.MaxPooling2D(2)(x)
x = layers.Conv2D(32, 3, activation='relu')(x)
x = layers.MaxPooling2D(2)(x)
x = layers.Conv2D(64, 3, activation='relu')(x)
x = layers.MaxPooling2D(2)(x)
x = layers.Flatten()(x)
x = layers.Dense(512, activation='relu')(x)
output = layers.Dense(1, activation='sigmoid')(x)
# Keras Model definition
# input = input feature map
# output = input feature map + stacked convolution/maxpooling layers + fully connected layer + sigmoid output layer
model = Model(image_input, output)
model.summary()
输出
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) (None, 150, 150, 3) 0
_________________________________________________________________
conv2d_4 (Conv2D) (None, 148, 148, 16) 448
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 74, 74, 16) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 72, 72, 32) 4640
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 36, 36, 32) 0
_________________________________________________________________
conv2d_6 (Conv2D) (None, 34, 34, 64) 18496
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 17, 17, 64) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 18496) 0
_________________________________________________________________
dense_1 (Dense) (None, 512) 9470464
_________________________________________________________________
dense_2 (Dense) (None, 1) 513
最佳答案
来自Keras documentation ,你可以看到填充是 default=valid
所以没有填充,步幅大小是 1。那么你的输出形状显然是 148 x 148。
要计算这个,您可以使用以下公式:
O = (W - K + 2P)/S + 1
其中 O 是输出高度/宽度,W 是输入高度/宽度,K 是过滤器大小,P 是填充,S 是步幅大小。
关于第二个参数,你有一个 16 的特征图,你的内核大小是 3 x 3,所以你有 16 x (3 x 3),也就是 144。然后你有三个颜色 channel ,所以 144 x 3 = 432,然后你需要添加 16 个偏差,这就是 448;)希望这有帮助!
关于python - 了解 model.summary Keras,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/45561306/