When we have stride =2  in a standard convolution layer we halve both the height and the width of the input tensor. Convolutional transpose layers use the same  principle but the difference is that instead of halving the width and height we are doubling them. As you can see in the **decoder code node** we use the Conv2DTranspose keras layer which implements this functionality. 


San Diego State University

__The decoder is a mirror image of the encoder, except instead of convolutional layers, we use convolutional transpose layers, as shown in the code. __

(Actually we don't have to write decoder as a mirror image of the encoder. But it is inevitable for the decoder to have exactly same size for the output image as we the input size of the encoder)
```python
     #<1> define the input to the decoder (the point in the latent space).
     decoder_input = Input(shape=(self.z_dim,), name='decoder_input')

        x = Dense(np.prod(shape_before_flattening))(decoder_input)
        x = Reshape(shape_before_flattening)(x)

        for i in range(self.n_layers_decoder):
            conv_t_layer = Conv2DTranspose(
                filters = self.decoder_conv_t_filters[i]
                , kernel_size = self.decoder_conv_t_kernel_size[i]
                , strides = self.decoder_conv_t_strides[i]
                , padding = 'same'
                , name = 'decoder_conv_t_' + str(i)
                )

            #<2>Stack convolutional transpose layers on top of each other.
            x = conv_t_layer(x)

            if i < self.n_layers_decoder - 1:
                x = LeakyReLU()(x)
                
                if self.use_batch_norm:
                    x = BatchNormalization()(x)
                
                if self.use_dropout:
                    x = Dropout(rate = 0.25)(x)
            else:
                x = Activation('sigmoid')(x)

        decoder_output = x
         
        #<3>The Keras model that defines the decoder—a model that takes a point in t 
        #the latent space and decodes it into the original image domain.
        self.decoder = Model(decoder_input, decoder_output)```

Learn Before

Related