TensorFlow Neural Net

from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
from six.moves import range
pickle_file = 'notMNIST.pickle'

with open(pickle_file, 'rb') as f:
    save = pickle.load(f)
    train_dataset = save['train_dataset']
    train_labels = save['train_labels']
    valid_dataset = save['valid_dataset']
    valid_labels = save['valid_labels']
    test_dataset = save['test_dataset']
    test_labels = save['test_labels']
    del save
    print('Training set', train_dataset.shape, train_labels.shape)
    print('Validation set', valid_dataset.shape, valid_labels.shape)
    print('Test set', test_dataset.shape, test_labels.shape)

image_size = 28
num_labels = 10

def reformat(dataset, labels):
    dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32)
    # Map 0 to [1.0, 0.0, 0.0 ...], 1 to [0.0, 1.0, 0.0 ...]
    labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
    return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)

batch_size = 128

graph = tf.Graph()
with graph.as_default():
    tf_train_dataset = tf.placeholder(tf.float32, shape=(batch_size, image_size * image_size))
    tf_train_labels = tf.placeholder(tf.int32, shape=(batch_size, num_labels))
    tf_valid_dataset = tf.constant(valid_dataset)
    tf_test_dataset = tf.constant(test_dataset)

    weights0 = tf.Variable(tf.truncated_normal([image_size**2, num_labels]))
    biases0 = tf.Variable(tf.zeros([num_labels]))

    hidden1 = tf.nn.relu(tf.matmul(tf_test_dataset, weights0) + biases0)

    weights1 = tf.Variable(tf.truncated_normal([num_labels, image_size * image_size]))
    biases1 = tf.Variable(tf.zeros([image_size**2]))

    hidden2 = tf.nn.relu(tf.matmul(hidden1, weights1) + biases1)


    logits = tf.matmul(hidden2, weights0) + biases0

    labels = tf.expand_dims(tf_train_labels, 1)

    indices = tf.expand_dims(tf.range(0, batch_size), 1)

    concated = tf.concat(1, [indices, tf.cast(labels,tf.int32)])

    onehot_labels = tf.sparse_to_dense(concated, tf.pack([batch_size, num_labels]), 1.0, 0.0)


    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits, onehot_labels))

    optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)

    train_prediction = tf.nn.softmax(logits)
    valid_prediction = tf.nn.softmax(tf.matmul(tf.nn.relu(tf.matmul(tf.nn.relu(tf.matmul(tf_valid_dataset,weights0) + biases0),weights1)+biases1),weights0)+biases0)
    test_prediction = tf.nn.softmax(tf.matmul(tf.nn.relu(tf.matmul(tf.nn.relu(tf.matmul(tf_test_dataset,weights0) + biases0),weights1)+biases1),weights0)+biases0)

num_steps = 3001

def accuracy(predictions, labels):
    return (100.0*np.sum(np.argmax(predictions, 1) == np.argmax(labels,1))/predictions.shape[0])

with tf.Session(graph=graph) as session:
    tf.initialize_all_variables().run()
    print('Initialized')
    for step in range(num_steps):
        offset = (step*batch_size)%(train_labels.shape[0] - batch_size)
        batch_data = train_dataset[offset:(offset+batch_size),:]
        batch_labels = train_labels[offset:(offset+batch_size),:]
        feed_dict = {tf_train_dataset : batch_data, tf_train_labels :batch_labels}
        _,l,predictions = session.run([optimizer, loss, train_prediction],feed_dict=feed_dict)
        if step%500 == 0:
            print('Loss at step %d: %f' % (step,l))
            print('Training accuracy: %.1f%%' % accuracy(predictions, batch_labels))
            print('Validation accuracy: %.1f%%' % accuracy(valid_prediction.eval(), valid_labels))
    print('Test accuracy: %.1f%%' % accuracy(test_prediction.eval(), test_labels))