def run_training(): """Train MNIST for a number of epochs.""" # Get the sets of images and labels for training, validation, and # test on MNIST. data_sets = input_data.read_data_sets(FLAGS.train_dir, FLAGS.fake_data) # Tell TensorFlow that the model will be built into the default Graph. with tf.Graph().as_default(): with tf.name_scope('input'): # Input data input_images = tf.constant(data_sets.train.images) input_labels = tf.constant(data_sets.train.labels) image, label = tf.train.slice_input_producer( [input_images, input_labels], num_epochs=FLAGS.num_epochs) label = tf.cast(label, tf.int32) images, labels = tf.train.batch([image, label], batch_size=FLAGS.batch_size) # Build a Graph that computes predictions from the inference model. logits = mnist.inference(images, FLAGS.hidden1, FLAGS.hidden2) # Add to the Graph the Ops for loss calculation. loss = mnist.loss(logits, labels) # Add to the Graph the Ops that calculate and apply gradients. train_op = mnist.training(loss, FLAGS.learning_rate) # Add the Op to compare the logits to the labels during evaluation. eval_correct = mnist.evaluation(logits, labels) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.merge_all_summaries() # Create a saver for writing training checkpoints. saver = tf.train.Saver() # Create the op for initializing variables. init_op = tf.initialize_all_variables() # Create a session for running Ops on the Graph. sess = tf.Session() # Run the Op to initialize the variables. sess.run(init_op) # Instantiate a SummaryWriter to output summaries and the Graph. summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def) # Start input enqueue threads. coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) # And then after everything is built, start the training loop. try: step = 0 while not coord.should_stop(): start_time = time.time() # Run one step of the model. _, loss_value = sess.run([train_op, loss]) duration = time.time() - start_time # Write the summaries and print an overview fairly often. if step % 100 == 0: # Print status to stdout. print 'Step %d: loss = %.2f (%.3f sec)' % ( step, loss_value, duration) # Update the events file. summary_str = sess.run(summary_op) summary_writer.add_summary(summary_str, step) step += 1 # Save a checkpoint periodically. if (step + 1) % 1000 == 0: print 'Saving' saver.save(sess, FLAGS.train_dir, global_step=step) step += 1 except tf.errors.OutOfRangeError: print 'Saving' saver.save(sess, FLAGS.train_dir, global_step=step) print 'Done training for %d epochs, %d steps.' % (FLAGS.num_epochs, step) finally: # When done, ask the threads to stop. coord.request_stop() # Wait for threads to finish. coord.join(threads) sess.close()
def run_training(): """Train MNIST for a number of steps.""" # Get the sets of images and labels for training, validation, and # test on MNIST. data_sets = input_data.read_data_sets(FLAGS.train_dir, FLAGS.fake_data) # Tell TensorFlow that the model will be built into the default Graph. with tf.Graph().as_default(): # Generate placeholders for the images and labels. images_placeholder, labels_placeholder = placeholder_inputs( FLAGS.batch_size) # Build a Graph that computes predictions from the inference model. logits = mnist.inference(images_placeholder, FLAGS.hidden1, FLAGS.hidden2) # Add to the Graph the Ops for loss calculation. loss = mnist.loss(logits, labels_placeholder) # Add to the Graph the Ops that calculate and apply gradients. train_op = mnist.training(loss, FLAGS.learning_rate) # Add the Op to compare the logits to the labels during evaluation. eval_correct = mnist.evaluation(logits, labels_placeholder) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.merge_all_summaries() # Create a saver for writing training checkpoints. saver = tf.train.Saver() # Create a session for running Ops on the Graph. sess = tf.Session() # Run the Op to initialize the variables. init = tf.initialize_all_variables() sess.run(init) # Instantiate a SummaryWriter to output summaries and the Graph. summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def) # And then after everything is built, start the training loop. for step in xrange(FLAGS.max_steps): start_time = time.time() # Fill a feed dictionary with the actual set of images and labels # for this particular training step. feed_dict = fill_feed_dict(data_sets.train, images_placeholder, labels_placeholder) # Run one step of the model. The return values are the activations # from the `train_op` (which is discarded) and the `loss` Op. To # inspect the values of your Ops or variables, you may include them # in the list passed to sess.run() and the value tensors will be # returned in the tuple from the call. _, loss_value = sess.run([train_op, loss], feed_dict=feed_dict) duration = time.time() - start_time # Write the summaries and print an overview fairly often. if step % 100 == 0: # Print status to stdout. print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration)) # Update the events file. summary_str = sess.run(summary_op, feed_dict=feed_dict) summary_writer.add_summary(summary_str, step) # Save a checkpoint and evaluate the model periodically. if (step + 1) % 1000 == 0 or (step + 1) == FLAGS.max_steps: saver.save(sess, FLAGS.train_dir, global_step=step) # Evaluate against the training set. print('Training Data Eval:') do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.train) # Evaluate against the validation set. print('Validation Data Eval:') do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.validation) # Evaluate against the test set. print('Test Data Eval:') do_eval(sess, eval_correct, images_placeholder, labels_placeholder, data_sets.test)
def run_training(): """Train MNIST for a number of epochs.""" # Get the sets of images and labels for training, validation, and # test on MNIST. data_sets = input_data.read_data_sets(FLAGS.train_dir, FLAGS.fake_data) # Tell TensorFlow that the model will be built into the default Graph. with tf.Graph().as_default(): with tf.name_scope('input'): # Input data input_images = tf.constant(data_sets.train.images) input_labels = tf.constant(data_sets.train.labels) image, label = tf.train.slice_input_producer( [input_images, input_labels], num_epochs=FLAGS.num_epochs) label = tf.cast(label, tf.int32) images, labels = tf.train.batch( [image, label], batch_size=FLAGS.batch_size) # Build a Graph that computes predictions from the inference model. logits = mnist.inference(images, FLAGS.hidden1, FLAGS.hidden2) # Add to the Graph the Ops for loss calculation. loss = mnist.loss(logits, labels) # Add to the Graph the Ops that calculate and apply gradients. train_op = mnist.training(loss, FLAGS.learning_rate) # Add the Op to compare the logits to the labels during evaluation. eval_correct = mnist.evaluation(logits, labels) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.merge_all_summaries() # Create a saver for writing training checkpoints. saver = tf.train.Saver() # Create the op for initializing variables. init_op = tf.initialize_all_variables() # Create a session for running Ops on the Graph. sess = tf.Session() # Run the Op to initialize the variables. sess.run(init_op) # Instantiate a SummaryWriter to output summaries and the Graph. summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, graph_def=sess.graph_def) # Start input enqueue threads. coord = tf.train.Coordinator() threads = tf.train.start_queue_runners(sess=sess, coord=coord) # And then after everything is built, start the training loop. try: step = 0 while not coord.should_stop(): start_time = time.time() # Run one step of the model. _, loss_value = sess.run([train_op, loss]) duration = time.time() - start_time # Write the summaries and print an overview fairly often. if step % 100 == 0: # Print status to stdout. print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value, duration)) # Update the events file. summary_str = sess.run(summary_op) summary_writer.add_summary(summary_str, step) step += 1 # Save a checkpoint periodically. if (step + 1) % 1000 == 0: print('Saving') saver.save(sess, FLAGS.train_dir, global_step=step) step += 1 except tf.errors.OutOfRangeError: print('Saving') saver.save(sess, FLAGS.train_dir, global_step=step) print('Done training for %d epochs, %d steps.' % (FLAGS.num_epochs, step)) finally: # When done, ask the threads to stop. coord.request_stop() # Wait for threads to finish. coord.join(threads) sess.close()