我的第一层是:
model.add(tf.keras.layers.Conv2D(filters=32, kernel_size=3, padding="same", activation="relu", input_shape=[32, 32, 3]))
模型摘要表中的参数数量:
Layer (type) Output Shape Param #
=================================================================
conv2d_4 (Conv2D) (None, 32, 32, 32) 896
根据我的理解,参数数量必须是:
(No of filters) X (Number of parameters in Kernel)
i.e. in my case ==> 32 X (3 X 3) = 288
但是它应该是896。怎么算出来的呢?
谢谢