如何在tf.keras中设置Conv2D的默认参数？

from tensorflow.keras.layers import Conv2D

class MyConv2D(Conv2D):
    def __init__(self, filters, kernel_size, strides=(1, 1), padding='valid', activation=None, **kwargs):
        super(MyConv2D, self).__init__(filters=filters, kernel_size=kernel_size, strides=strides, padding=padding, activation=activation, **kwargs)
        self.my_default_param = 'default_value'

# 使用自定义的MyConv2D类
conv = MyConv2D(filters=32, kernel_size=(3, 3))