In [9]:

    

import tensorflow as tf

# The file path to save the data
save_file = './models/model.ckpt'

# Two Tensor Variables: weights and bias
weights = tf.Variable(tf.truncated_normal([2, 3]))
bias = tf.Variable(tf.truncated_normal([3]))

# Class used to save and/or restore Tensor Variables
saver = tf.train.Saver()

with tf.Session() as sess:
    # Initialize all the Variables
    sess.run(tf.global_variables_initializer())

    # Show the values of weights and bias
    print('Weights:')
    print(sess.run(weights))
    print('Bias:')
    print(sess.run(bias))

    # Save the model
    saver.save(sess, save_file)


    

    




Weights:
[[ 0.52065289  0.52489907 -0.53488785]
 [-0.39257374  0.22524773 -1.34971642]]
Bias:
[ 0.45921239 -0.10951263  0.81228799]

In [10]:

    

# Remove the previous weights and bias
tf.reset_default_graph()

# Two Variables: weights and bias
weights = tf.Variable(tf.truncated_normal([2, 3]))
bias = tf.Variable(tf.truncated_normal([3]))

# Class used to save and/or restore Tensor Variables
saver = tf.train.Saver()

with tf.Session() as sess:
    # Load the weights and bias
    saver.restore(sess, save_file)

    # Show the values of weights and bias
    print('Weight:')
    print(sess.run(weights))
    print('Bias:')
    print(sess.run(bias))


    

    




Weight:
[[ 0.26662284 -1.53644907 -1.28939474]
 [-0.58819622  0.00474699  0.25624454]]
Bias:
[-1.58836102 -0.95301056  0.37974098]

In [11]:

    

# Remove previous Tensors and Operations
tf.reset_default_graph()

from tensorflow.examples.tutorials.mnist import input_data
import numpy as np

learning_rate = 0.001
n_input = 784  # MNIST data input (img shape: 28*28)
n_classes = 10  # MNIST total classes (0-9 digits)

# Import MNIST data
mnist = input_data.read_data_sets('./datasets/ud730/mnist', one_hot=True)

# Features and Labels
features = tf.placeholder(tf.float32, [None, n_input])
labels = tf.placeholder(tf.float32, [None, n_classes])

# Weights & bias
weights = tf.Variable(tf.random_normal([n_input, n_classes]))
bias = tf.Variable(tf.random_normal([n_classes]))

# Logits - xW + b
logits = tf.add(tf.matmul(features, weights), bias)

# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=labels))
optimizer = tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cost)

# Calculate accuracy
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))


    

    




Extracting ./datasets/ud730/mnist/train-images-idx3-ubyte.gz
Extracting ./datasets/ud730/mnist/train-labels-idx1-ubyte.gz
Extracting ./datasets/ud730/mnist/t10k-images-idx3-ubyte.gz
Extracting ./datasets/ud730/mnist/t10k-labels-idx1-ubyte.gz

In [12]:

    

import math

save_file = './models/train_model.ckpt'
batch_size = 128
n_epochs = 100

saver = tf.train.Saver()

# Launch the graph
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())

    # Training cycle
    for epoch in range(n_epochs):
        total_batch = math.ceil(mnist.train.num_examples / batch_size)

        # Loop over all batches
        for i in range(total_batch):
            batch_features, batch_labels = mnist.train.next_batch(batch_size)
            sess.run(
                optimizer,
                feed_dict={features: batch_features, labels: batch_labels})

        # Print status for every 10 epochs
        if epoch % 10 == 0:
            valid_accuracy = sess.run(
                accuracy,
                feed_dict={
                    features: mnist.validation.images,
                    labels: mnist.validation.labels})
            print('Epoch {:<3} - Validation Accuracy: {}'.format(
                epoch,
                valid_accuracy))

    # Save the model
    saver.save(sess, save_file)
    print('Trained Model Saved.')


    

    




Epoch 0   - Validation Accuracy: 0.12720000743865967
Epoch 10  - Validation Accuracy: 0.26600000262260437
Epoch 20  - Validation Accuracy: 0.40540000796318054
Epoch 30  - Validation Accuracy: 0.506600022315979
Epoch 40  - Validation Accuracy: 0.5740000009536743
Epoch 50  - Validation Accuracy: 0.6197999715805054
Epoch 60  - Validation Accuracy: 0.6567999720573425
Epoch 70  - Validation Accuracy: 0.6827999949455261
Epoch 80  - Validation Accuracy: 0.7052000164985657
Epoch 90  - Validation Accuracy: 0.7188000082969666
Trained Model Saved.

In [13]:

    

saver = tf.train.Saver()

# Launch the graph
with tf.Session() as sess:
    saver.restore(sess, save_file)

    test_accuracy = sess.run(
        accuracy,
        feed_dict={features: mnist.test.images, labels: mnist.test.labels})

print('Test Accuracy: {}'.format(test_accuracy))


    

    




Test Accuracy: 0.7357000112533569

In [ ]: