In this implementation, we will be using more layers in the encoder and decoder part, and the reason for this is the new complexity that we have added to the input.
The next model is exactly the same as the previous CAE but with extra layers that will help us to reconstruct a noise-free image from a noisy one.
So let's go ahead and build this architecture:
learning_rate = 0.001
# Define the placeholder variable sfor the input and target values
inputs_values = tf.placeholder(tf.float32, (None, 28, 28, 1), name='inputs_values')
targets_values = tf.placeholder(tf.float32, (None, 28, 28, 1), name='targets_values')
# Defining the Encoder part of the netowrk
# Defining the first convolution layer in the encoder parrt
# The output tenosor will be in the shape of 28x28x32
conv_layer_1 = tf.layers.conv2d(inputs=inputs_values, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# The output tenosor will be in the shape of 14x14x32
maxpool_layer_1 = tf.layers.max_pooling2d(conv_layer_1, pool_size=(2,2), strides=(2,2), padding='same')
# The output tenosor will be in the shape of 14x14x32
conv_layer_2 = tf.layers.conv2d(inputs=maxpool_layer_1, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# The output tenosor will be in the shape of 7x7x32
maxpool_layer_2 = tf.layers.max_pooling2d(conv_layer_2, pool_size=(2,2), strides=(2,2), padding='same')
# The output tenosor will be in the shape of 7x7x16
conv_layer_3 = tf.layers.conv2d(inputs=maxpool_layer_2, filters=16, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# The output tenosor will be in the shape of 4x4x16
encoding_layer = tf.layers.max_pooling2d(conv_layer_3, pool_size=(2,2), strides=(2,2), padding='same')
# Defining the Decoder part of the netowrk
# Defining the first upsampling layer in the decoder part
# The output tenosor will be in the shape of 7x7x16
upsample_layer_1 = tf.image.resize_images(encoding_layer, size=(7,7), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# The output tenosor will be in the shape of 7x7x16
conv_layer_4 = tf.layers.conv2d(inputs=upsample_layer_1, filters=16, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# The output tenosor will be in the shape of 14x14x16
upsample_layer_2 = tf.image.resize_images(conv_layer_4, size=(14,14), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# The output tenosor will be in the shape of 14x14x32
conv_layer_5 = tf.layers.conv2d(inputs=upsample_layer_2, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# The output tenosor will be in the shape of 28x28x32
upsample_layer_3 = tf.image.resize_images(conv_layer_5, size=(28,28), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
# The output tenosor will be in the shape of 28x28x32
conv_layer_6 = tf.layers.conv2d(inputs=upsample_layer_3, filters=32, kernel_size=(3,3), padding='same', activation=tf.nn.relu)
# The output tenosor will be in the shape of 28x28x1
logits_layer = tf.layers.conv2d(inputs=conv_layer_6, filters=1, kernel_size=(3,3), padding='same', activation=None)
# feeding the logits values to the sigmoid activation function to get the reconstructed images
decoding_layer = tf.nn.sigmoid(logits_layer)
# feeding the logits to sigmoid while calculating the cross entropy
model_loss = tf.nn.sigmoid_cross_entropy_with_logits(labels=targets_values, logits=logits_layer)
# Getting the model cost and defining the optimizer to minimize it
model_cost = tf.reduce_mean(model_loss)
model_optimizer = tf.train.AdamOptimizer(learning_rate).minimize(model_cost)
Now we have a more complex or deeper version of the convolutional model.