如何在 conv2d 层中使用 PReLU

Question

I'm trying to use PReLU activation function in the below code line, kindly let me know how to do it.

x = Conv2D(64, (3,3), padding='same', strides= (2,2), "activation = tf.keras.activations.sigmoid", name='layer1')(x)
x = MaxPooling2D(pool_size=(2,2))(x)

Answer 1

You can pass it as a layer, like this:

x = Conv2D(64, (3,3), padding='same', strides= (2,2))(x)
x = tf.keras.layers.PReLU()(x)
x = MaxPooling2D(pool_size=(2,2))(x)

As dscribed in the docs