def evaluate(): """Eval CIFAR-10 for a number of steps.""" with tf.Graph().as_default() as g: # Get images and labels for CIFAR-10. data_load_time = time.time() images, labels = get_inputs(False) data_load_time = time.time() - data_load_time # Build a Graph that computes the logits predictions from the # inference model. logits = inference(images) # Calculate predictions. top_k_op = tf.nn.in_top_k(logits, labels, 1) # Restore the moving average version of the learned variables for eval. variable_averages = tf.train.ExponentialMovingAverage( MOVING_AVERAGE_DECAY) variables_to_restore = variable_averages.variables_to_restore() saver = tf.train.Saver(variables_to_restore) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.merge_all_summaries() summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir, g) test_time = time.time() while True: eval_once(saver, summary_writer, top_k_op, summary_op) if FLAGS.run_once: break time.sleep(FLAGS.eval_interval_secs) return time.time() - test_time, data_load_time
def evaluate(): """Eval CIFAR-10 for a number of steps.""" with tf.Graph().as_default() as g: # Get images and labels for CIFAR-10. data_load_time = time.time() images, labels = get_inputs(False) data_load_time = time.time() - data_load_time # Build a Graph that computes the logits predictions from the # inference model. logits = inference(images) # Calculate predictions. top_k_op = tf.nn.in_top_k(logits, labels, 1) # Restore the moving average version of the learned variables for eval. variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY) variables_to_restore = variable_averages.variables_to_restore() saver = tf.train.Saver(variables_to_restore) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.merge_all_summaries() summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir, g) test_time = time.time() while True: eval_once(saver, summary_writer, top_k_op, summary_op) if FLAGS.run_once: break time.sleep(FLAGS.eval_interval_secs) return time.time() - test_time, data_load_time
def train(): """Train CIFAR-10 for a number of steps.""" with tf.Graph().as_default(): global_step = tf.Variable(0, trainable=False) # Get images and labels for CIFAR-10. data_load_time = time.time() images, labels = get_inputs(True) data_load_time = time.time() - data_load_time # Build a Graph that computes the logits predictions from the # inference model. logits = inference(images) # Calculate loss. loss = score(logits, labels) # Build a Graph that trains the model with one batch of examples and # updates the model parameters. train_op = train_setup(loss, global_step) # Create a saver. saver = tf.train.Saver(tf.all_variables()) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.merge_all_summaries() # Build an initialization operation to run below. init = tf.initialize_all_variables() # Start running operations on the Graph. config = tf.ConfigProto( log_device_placement=FLAGS.log_device_placement) config.gpu_options.per_process_gpu_memory_fraction = 0 sess = tf.Session(config=config) sess.run(init) # Start the queue runners. tf.train.start_queue_runners(sess=sess) summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph) train_time = time.time() for iter in xrange(FLAGS.max_iter): start_time = time.time() _, loss_value = sess.run([train_op, loss]) duration = time.time() - start_time assert not np.isnan(loss_value), 'Model diverged with loss = NaN' if iter % 10 == 0: num_examples_per_step = FLAGS.batch_size examples_per_sec = num_examples_per_step / duration sec_per_batch = float(duration) format_str = ( '%s: step %d, loss = %.2f (%.1f examples/sec; %.3f ' 'sec/batch)') print(format_str % (datetime.now(), iter, loss_value, examples_per_sec, sec_per_batch)) if iter % 100 == 0: summary_str = sess.run(summary_op) summary_writer.add_summary(summary_str, iter) # Save the model checkpoint periodically. if iter % 1000 == 0 or (iter + 1) == FLAGS.max_iter: checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt') saver.save(sess, checkpoint_path, global_step=iter) return time.time() - train_time, data_load_time
def train(): """Train CIFAR-10 for a number of steps.""" with tf.Graph().as_default(): global_step = tf.Variable(0, trainable=False) # Get images and labels for CIFAR-10. data_load_time = time.time() images, labels = get_inputs(True) data_load_time = time.time() - data_load_time # Build a Graph that computes the logits predictions from the # inference model. logits = inference(images) # Calculate loss. loss = score(logits, labels) # Build a Graph that trains the model with one batch of examples and # updates the model parameters. train_op = train_setup(loss, global_step) # Create a saver. saver = tf.train.Saver(tf.all_variables()) # Build the summary operation based on the TF collection of Summaries. summary_op = tf.merge_all_summaries() # Build an initialization operation to run below. init = tf.initialize_all_variables() # Start running operations on the Graph. config=tf.ConfigProto(log_device_placement=FLAGS.log_device_placement) config.gpu_options.per_process_gpu_memory_fraction=0 sess = tf.Session(config=config) sess.run(init) # Start the queue runners. tf.train.start_queue_runners(sess=sess) summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph) train_time = time.time() for iter in xrange(FLAGS.max_iter): start_time = time.time() _, loss_value = sess.run([train_op, loss]) duration = time.time() - start_time assert not np.isnan(loss_value), 'Model diverged with loss = NaN' if iter % 10 == 0: num_examples_per_step = FLAGS.batch_size examples_per_sec = num_examples_per_step / duration sec_per_batch = float(duration) format_str = ('%s: step %d, loss = %.2f (%.1f examples/sec; %.3f ' 'sec/batch)') print (format_str % (datetime.now(), iter, loss_value, examples_per_sec, sec_per_batch)) if iter % 100 == 0: summary_str = sess.run(summary_op) summary_writer.add_summary(summary_str, iter) # Save the model checkpoint periodically. if iter % 1000 == 0 or (iter + 1) == FLAGS.max_iter: checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt') saver.save(sess, checkpoint_path, global_step=iter) return time.time() - train_time, data_load_time