Deep Learning By Example

Building the model

In this implementation, we will be using convolution layers with stride 1, and the padding parameter is set to be the same. By this, we won't change the height or width of the image. Also, we are using a set of max pooling layers to reduce the width and height of the image and hence building a compressed lower representation of the image.

So let's go ahead and build the core of our network:

learning_rate = 0.001# Define the placeholder variable sfor the input and target valuesinputs_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 ...