def evaluate():
os.environ['CUDA_VISIBLE_DEVICES'] = str(FLAGS.gpuid)
with tf.Graph().as_default() as g:
images, labels = data_input.inputs(data_dir=FLAGS.data_dir,
batch_size=FLAGS.eval_batch_size,
num_tags=num_tags)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = model.inference(images,
is_training=False,
num_classes=num_tags)
# Calculate predictions.
prob_op = tf.sigmoid(logits)
# Restore the moving average version of the learned variables for eval.
saver = tf.train.Saver(tf.global_variables())
summary_op = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter(eval_dir, g)
while True:
eval_once(saver, summary_writer, prob_op, labels, summary_op)
if FLAGS.run_once:
break
time.sleep(FLAGS.eval_interval_secs)
def inputs(eval_data, sessid):
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
images, labels, i_paths = data_input.inputs(eval_data=eval_data,
batch_size=FLAGS.batch_size, sessid = sessid)
labels = tf.cast(tf.divide(labels,255),tf.int32)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels, i_paths
def inputs(eval_data):
"""Construct input for data evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
labels: Labels. 1D tensor of [batch_size] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
#data_dir = os.path.join(FLAGS.data_dir, 'cifar-10-batches-bin')
return data_input.inputs(eval_data=eval_data, data_dir=FLAGS.data_dir, batch_size=FLAGS.batch_size)
def inputs(eval_data, sessid):
"""Construct input for BBBC006 evaluation using the Reader ops.
Args:
eval_data: bool, indicating if one should use the train or eval data set.
Returns:
images: Images. 4D tensor of [batch_size, IMAGE_WIDTH, IMAGE_HEIGHT, 1] size.
labels: Labels. 4D tensor of [batch_size, IMAGE_WIDTH, IMAGE_HEIGHT, 2] size.
Raises:
ValueError: If no data_dir
"""
if not FLAGS.data_dir:
raise ValueError('Please supply a data_dir')
images, labels, i_paths = data_input.inputs(eval_data=eval_data,
batch_size=FLAGS.batch_size,
sessid=sessid)
labels = tf.cast(tf.divide(labels, 255), tf.int32)
if FLAGS.use_fp16:
images = tf.cast(images, tf.float16)
labels = tf.cast(labels, tf.float16)
return images, labels, i_paths
def run_training():
"""Train model for a number of steps."""
# Get the sets of images and labels for training, validation, and
# test on MNIST.
# Tell TensorFlow that the model will be built into the default Graph.
train_dir = os.path.join(FLAGS.model_dir, FLAGS.name)
with open('kitti.json', 'r') as f:
hypes = json.load(f)
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
with tf.name_scope('Input'):
q = data_input.create_queues(hypes)
image_batch, label_batch = data_input.inputs(
q, 'train', hypes['solver']['batch_size'])
# Generate placeholders for the images and labels.
keep_prob = utils.placeholder_inputs()
# Build a Graph that computes predictions from the inference model.
logits = model.inference(image_batch, keep_prob)
# Add to the Graph the Ops for loss calculation.
loss = model.loss(logits, label_batch)
# Add to the Graph the Ops that calculate and apply gradients.
train_op = model.training(loss,
global_step=global_step,
learning_rate=FLAGS.learning_rate)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = model.evaluation(logits, label_batch)
# 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)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
data_input.start_enqueuing_threads(hypes, q, sess)
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer = tf.train.SummaryWriter(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 = utils.fill_feed_dict(keep_prob, train=True)
# 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)
# Write the summaries and print an overview fairly often.
if step % 100 == 0:
# Print status to stdout.
duration = time.time() - start_time
examples_per_sec = hypes['solver']['batch_size'] / duration
sec_per_batch = float(duration)
print(
'Step %d: loss = %.2f ( %.3f sec (per Batch); %.1f examples/sec;)'
% (step, loss_value, sec_per_batch, examples_per_sec))
# 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:
checkpoint_path = os.path.join(train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
# Evaluate against the training set.
if (step + 1) % 10000 == 0 or (step + 1) == FLAGS.max_steps:
print('Training Data Eval:')
utils.do_eval(sess, eval_correct, keep_prob,
data_input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN)
def evaluate_last():
"""Loads the model and runs evaluation
"""
with tf.Graph().as_default():
# Get images and labels for CIFAR-10.
model_dir = os.path.join(FLAGS.model_dir, FLAGS.name)
eval_data = FLAGS.eval_data == 'test'
images, labels = data_input.inputs(eval_data=eval_data,
data_dir=FLAGS.data_dir,
batch_size=FLAGS.batch_size)
#images, labels = data_input.distorted_inputs(eval_data=eval_data, data_dir=FLAGS.data_dir,
# batch_size=FLAGS.batch_size)
# Generate placeholders for the images and labels.
keep_prob = utils.placeholder_inputs(FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
logits = model.inference(images, keep_prob)
# Add to the Graph the Ops for loss calculation.
loss = model.loss(logits, labels)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = model.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 a session for running Ops on the Graph.
sess = tf.Session()
# Restore the moving average version of the learned variables for eval.
# variable_averages = tf.train.ExponentialMovingAverage(
# cifar10.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()
#graph_def = tf.get_default_graph().as_graph_def()
#summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir,
# graph_def=graph_def)
# Run the Op to initialize the variables.
init = tf.initialize_all_variables()
sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
print(model_dir)
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
print("No checkpoints found! ")
exit(1)
print("Doing Evaluation with lots of data")
utils.do_eval(sess=sess,
eval_correct=eval_correct,
keep_prob=keep_prob,
num_examples=data_input.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL)
def run_training():
"""Train model for a number of steps."""
# Get the sets of images and labels for training, validation, and
# test on MNIST.
# Tell TensorFlow that the model will be built into the default Graph.
train_dir = os.path.join(FLAGS.model_dir,FLAGS.name)
with open('kitti.json', 'r') as f:
hypes = json.load(f)
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
with tf.name_scope('Input'):
q = data_input.create_queues(hypes)
image_batch, label_batch = data_input.inputs(q, 'train', hypes['solver']['batch_size'])
# Generate placeholders for the images and labels.
keep_prob = utils.placeholder_inputs()
# Build a Graph that computes predictions from the inference model.
logits = model.inference(image_batch, keep_prob)
# Add to the Graph the Ops for loss calculation.
loss = model.loss(logits, label_batch)
# Add to the Graph the Ops that calculate and apply gradients.
train_op = model.training(loss, global_step=global_step, learning_rate=FLAGS.learning_rate)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = model.evaluation(logits, label_batch)
# 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)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
data_input.start_enqueuing_threads(hypes, q, sess)
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer = tf.train.SummaryWriter(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 = utils.fill_feed_dict(keep_prob,
train = True)
# 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)
# Write the summaries and print an overview fairly often.
if step % 100 == 0:
# Print status to stdout.
duration = time.time() - start_time
examples_per_sec = hypes['solver']['batch_size'] / duration
sec_per_batch = float(duration)
print('Step %d: loss = %.2f ( %.3f sec (per Batch); %.1f examples/sec;)' % (step, loss_value,
sec_per_batch, examples_per_sec))
# 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:
checkpoint_path = os.path.join(train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path , global_step=step)
# Evaluate against the training set.
if (step + 1) % 10000 == 0 or (step + 1) == FLAGS.max_steps:
print('Training Data Eval:')
utils.do_eval(sess,
eval_correct,
keep_prob,
data_input.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN)
def evaluate_last():
"""Loads the model and runs evaluation
"""
with tf.Graph().as_default():
# Get images and labels for CIFAR-10.
model_dir = os.path.join(FLAGS.model_dir,FLAGS.name)
eval_data = FLAGS.eval_data == 'test'
images, labels = data_input.inputs(eval_data=eval_data, data_dir=FLAGS.data_dir,
batch_size=FLAGS.batch_size)
#images, labels = data_input.distorted_inputs(eval_data=eval_data, data_dir=FLAGS.data_dir,
# batch_size=FLAGS.batch_size)
# Generate placeholders for the images and labels.
keep_prob = utils.placeholder_inputs(FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
logits = model.inference(images, keep_prob)
# Add to the Graph the Ops for loss calculation.
loss = model.loss(logits, labels)
# Calculate predictions.
top_k_op = tf.nn.in_top_k(logits, labels, 1)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = model.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 a session for running Ops on the Graph.
sess = tf.Session()
# Restore the moving average version of the learned variables for eval.
# variable_averages = tf.train.ExponentialMovingAverage(
# cifar10.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()
#graph_def = tf.get_default_graph().as_graph_def()
#summary_writer = tf.train.SummaryWriter(FLAGS.eval_dir,
# graph_def=graph_def)
# Run the Op to initialize the variables.
init = tf.initialize_all_variables()
sess.run(init)
# Start the queue runners.
tf.train.start_queue_runners(sess=sess)
print(model_dir)
ckpt = tf.train.get_checkpoint_state(model_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
else:
print("No checkpoints found! ")
exit(1)
print("Doing Evaluation with lots of data")
utils.do_eval(sess=sess,
eval_correct=eval_correct,
keep_prob=keep_prob,
num_examples=data_input.NUM_EXAMPLES_PER_EPOCH_FOR_EVAL)
