training/train_unsupervised.py [266:281]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    x3 = LeakyReLU(0.1)(x3)
    x = Concatenate(axis=-1)([x1,x2,x3])
    x = Conv2D(num_filters_per_layer, kernel_size=(1,1), strides=(1,1), padding="same", activation=None)(x)
    x = BatchNormalization()(x)
    x = LeakyReLU(0.1)(x)

    x1 = Conv2D(num_filters_per_layer, kernel_size=(3,3), strides=(1,1), padding="same", activation=None)(x)
    x1 = LeakyReLU(0.1)(x1)
    x2 = Conv2D(num_filters_per_layer, kernel_size=(5,5), strides=(1,1), padding="same", activation=None)(x)
    x2 = LeakyReLU(0.1)(x2)
    x3 = Conv2D(num_filters_per_layer, kernel_size=(7,7), strides=(1,1), padding="same", activation=None)(x)
    x3 = LeakyReLU(0.1)(x3)
    x = Concatenate(axis=-1)([x1,x2,x3])
    x = Conv2D(num_filters_per_layer, kernel_size=(1,1), strides=(1,1), padding="same", activation=None)(x)
    x = BatchNormalization()(x)
    x = LeakyReLU(0.1)(x)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/train_unsupervised.py [277:292]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    x3 = LeakyReLU(0.1)(x3)
    x = Concatenate(axis=-1)([x1,x2,x3])
    x = Conv2D(num_filters_per_layer, kernel_size=(1,1), strides=(1,1), padding="same", activation=None)(x)
    x = BatchNormalization()(x)
    x = LeakyReLU(0.1)(x)

    x1 = Conv2D(num_filters_per_layer, kernel_size=(3,3), strides=(1,1), padding="same", activation=None)(x)
    x1 = LeakyReLU(0.1)(x1)
    x2 = Conv2D(num_filters_per_layer, kernel_size=(5,5), strides=(1,1), padding="same", activation=None)(x)
    x2 = LeakyReLU(0.1)(x2)
    x3 = Conv2D(num_filters_per_layer, kernel_size=(7,7), strides=(1,1), padding="same", activation=None)(x)
    x3 = LeakyReLU(0.1)(x3)
    x = Concatenate(axis=-1)([x1,x2,x3])
    x = Conv2D(num_filters_per_layer, kernel_size=(1,1), strides=(1,1), padding="same", activation=None)(x)
    x = BatchNormalization()(x)
    x = LeakyReLU(0.1)(x)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -