Stochastic Gradient Descent and 2 layer neural network

sgd.py

batch_size = 128
valid_dataset = valid_dataset[:batch_size]
valid_labels = valid_labels[:batch_size]
test_dataset = test_dataset[:batch_size]
test_labels = test_labels[:batch_size]

graph = tf.Graph()
with graph.as_default():

  # Input data. For the training data, we use a placeholder that will be fed
  # at run time with a training minibatch.
  tf_train_dataset = tf.placeholder(tf.float32,
                                    shape=(batch_size, image_size * image_size))
  tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
  tf_valid_dataset = tf.constant(valid_dataset)
  tf_test_dataset = tf.constant(test_dataset)
  
  # Variables.
  weights1 = tf.Variable(
    tf.truncated_normal([image_size * image_size, batch_size]))
  biases1 = tf.Variable(tf.zeros([batch_size]))

  weights2 = tf.Variable(
    tf.truncated_normal([batch_size, num_labels]))
  biases2 = tf.Variable(tf.zeros([batch_size, num_labels]))
  
  # Training computation.
  layer1 = tf.matmul(tf_train_dataset, weights1) + biases1
  layer1 = tf.nn.relu(layer1)

  layer2 = tf.matmul(layer1, weights2) + biases2

  loss = tf.reduce_mean(
  	tf.nn.softmax_cross_entropy_with_logits(labels=tf_train_labels, logits=layer2))
  
  # Optimizer.
  optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
  
  # Predictions for the training, validation, and test data.
  train_prediction = tf.nn.softmax(layer2)
  valid_prediction = tf.nn.softmax(
    tf.matmul(tf.nn.relu(
    	tf.matmul(tf_valid_dataset, weights1) + biases1), weights2) + biases2)
  test_prediction = tf.nn.softmax(
  	tf.matmul(tf.nn.relu(
  		tf.matmul(tf_test_dataset, weights1) + biases1), weights2) + biases2)

num_steps = 3001

with tf.Session(graph=graph) as session:
  tf.global_variables_initializer().run()
  print("Initialized")
  for step in range(num_steps):
    # Pick an offset within the training data, which has been randomized.
    # Note: we could use better randomization across epochs.
    offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
    # Generate a minibatch.
    batch_data = train_dataset[offset:(offset + batch_size), :]
    batch_labels = train_labels[offset:(offset + batch_size), :]
    # Prepare a dictionary telling the session where to feed the minibatch.
    # The key of the dictionary is the placeholder node of the graph to be fed,
    # and the value is the numpy array to feed to it.
    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("Minibatch loss at step %d: %f" % (step, l))
      print("Minibatch 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))