Нужен ли пользовательскому слою Keras from_config, если он внутри себя создает другой пользовательский слой? ⇐ Python

[Anonymous]

Я работаю с Keras 3 и у меня есть два пользовательских слоя: SingleConv и DoubleConv. Оба зарегистрированы с помощью @keras.saving.register_keras_serializable.
DoubleConv не принимает экземпляр слоя в качестве аргумента. Вместо этого он принимает базовые типы (int, str) и создает экземпляры SingleConv внутри своего __init__.
Согласно документации Keras:

"Для более сложных объектов, таких как слои или модели, передаваемые в __init__, десериализация должна обрабатываться явно..."

Поскольку я передача int и str в DoubleConv, но они используются для внутреннего создания пользовательского SingleConv, нужно ли мне реализовать from_config для DoubleConv из-за внутреннего использования SingleConv?
@keras.saving.register_keras_serializable(package="MyLayers", name="DoubleConv")
class DoubleConv(keras.layers.Layer):
"""
A module consisting of two consecutive convolution layers (e.g. BatchNorm3d+ReLU+Conv3d).
We use (Conv3d+ReLU) by default.
This can be changed however by providing the 'order' argument, e.g. in order
to change to Conv3d+BatchNorm3d+ELU use order='cbe'.

Args:
in_channels (int): number of input channels
out_channels (int): number of output channels
encoder (bool): if True we're in the encoder path, otherwise we're in the decoder
kernel_size (int or tuple): size of the convolving kernel
order (string): determines the order of layers, e.g.
'cr' -> conv + ReLU
'crb' -> conv + ReLU + batchnorm
'cl' -> conv + LeakyReLU
'ce' -> conv + ELU
num_groups (int): number of groups for the GroupNorm
upscale (int): number of the convolution to upscale in encoder if DoubleConv, default: 2
dropout_prob (float or tuple): dropout probability for each convolution, default 0.1
is3d (bool): if True use Conv3d instead of Conv2d layers
"""
def __init__(self, in_channels, out_channels, encoder=True, padding='same', kernel_size=3, order='cr',
dropout_prob=0.1, upscale=2, is3d=True, **kwargs):
super().__init__(**kwargs)

self.in_channels = in_channels
self.out_channels = out_channels
self.encoder = encoder
self.padding = padding
self.kernel_size = kernel_size
self.order = order
self.dropout_prob = dropout_prob
self.upscale = upscale
self.is3d = is3d

if self.encoder:
# we're in the encoder path
conv1_in_channels = self.in_channels
if upscale == 1:
conv1_out_channels = self.out_channels
else:
conv1_out_channels = self.out_channels // 2
if conv1_out_channels < self.in_channels:
conv1_out_channels = self.in_channels

conv2_in_channels = conv1_out_channels
conv2_out_channels = self.out_channels

else:
# we're in the decoder path, decrease the number of channels in the 1st convolution
conv1_in_channels, conv1_out_channels = self.in_channels, self.out_channels
conv2_in_channels, conv2_out_channels = self.out_channels, self.out_channels

# check if dropout_prob is a tuple and if so
# split it for different dropout probabilities for each convolution.

if isinstance(self.dropout_prob, list) or isinstance(self.dropout_prob, tuple):
dropout_prob1 = self.dropout_prob[0]
dropout_prob2 = self.dropout_prob[1]
else:
dropout_prob1 = dropout_prob2 = self.dropout_prob

self.conv1 = SingleConv(out_channels=conv1_out_channels, padding=self.padding, kernel_size=self.kernel_size, order=self.order,
dropout_prob=dropout_prob1, is3d= self.is3d)

self.conv2 = SingleConv( out_channels=conv2_out_channels, padding=self.padding, kernel_size=self.kernel_size, order=self.order,
dropout_prob=dropout_prob2, is3d=self.is3d)

def call(self, inputs, training=None):
x = self.conv1(inputs, training=training)
return self.conv2(x, training=training)

def get_config(self):
config = super().get_config()
# Update the config with the custom layer's parameters
config.update(
{
"in_channels": self.in_channels,
"out_channels": self.out_channels,
"encoder": self.encoder,
"padding": self.padding,
"kernel_size": self.kernel_size,
"order": self.order,
"dropout_prob": self.dropout_prob,
"upscale": self.upscale,
"is3d": self.is3d,
}
)
return config


Подробнее здесь: https://stackoverflow.com/questions/798 ... custom-lay