Visualization

As concerns, the TensorBoard analysis, from the folder where the source has been executed, you should digit:

 $> Tensorboard --logdir = 'log_simple_stats_5_layers_relu_softmax'

Then open the browser at localhost to visualize TensorBoard's starting page.

In the following figure, we show the trend's accuracy over the number of examples of the training set:

Accuracy function over train set

You can easily see how the accuracy, after a bad initial trend, begins a rapid progressive improvement after about 1000 examples.

Source code for the ReLU classifier

Here we have the entire code for the implemented ReLU classifier:

import mnist_data 
import tensorflow as tf 
import math 

logs_path = 'log_simple_stats_5_layers_relu_softmax' 
batch_size = 100 
learning_rate = 0.5 
training_epochs = 10 

mnist = mnist_data.read_data_sets("data") 

X = tf.placeholder(tf.float32, [None, 28, 28, 1]) 
Y_ = tf.placeholder(tf.float32, [None, 10]) 
lr = tf.placeholder(tf.float32) 

# five layers and their...