def evaluate(train_dir):
"""Loads the model and runs evaluation
"""
target_dir = os.path.join(train_dir, "model_files")
params = imp.load_source("params", os.path.join(target_dir, "params.py"))
data_input = imp.load_source("input", os.path.join(target_dir, "input.py"))
network = imp.load_source("network", os.path.join(target_dir, "network.py"))
with tf.Graph().as_default():
# Retrieve images and labels
eval_data = FLAGS.eval_data == 'test'
images, labels = data_input.inputs(eval_data=eval_data, data_dir=utils.cfg.data_dir,
batch_size=params.batch_size)
# Generate placeholders for the images and labels.
keep_prob = utils.placeholder_inputs(params.batch_size)
# Build a Graph that computes predictions from the inference model.
logits = network.inference(images, keep_prob)
# Add to the Graph the Ops for loss calculation.
loss = network.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 = network.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()
# 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)
ckpt = tf.train.get_checkpoint_state(train_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=params.num_examples_per_epoch_for_eval,
params=params,
name="eval")
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 BinaryConnect."""
# Get the sets of images and labels for training, validation, and
# test on CIFAR10.
data_sets = cifar10.read_data_sets(dst_dir='./dataset',
validation_size=5000)
# 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, train_placeholder = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes predictions from the inference model.
logits = bc.inference_bin(images_placeholder, train_placeholder,
stochastic=FLAGS.stochastic,
use_bnorm=True) \
if FLAGS.binary \
else bc.inference_ref(images_placeholder, train_placeholder,
use_bnorm=True)
# Add to the Graph the Ops for loss calculation.
loss = bc.loss(logits, labels_placeholder)
# Add to the Graph the Ops that calculate and apply gradients.
train_op = bc.training(loss, FLAGS.learning_rate)
# Add the Op to compare the logits to the labels during evaluation.
eval_metric = bc.evaluation(logits, labels_placeholder)
# Add a placeholder for logging execution time
# frequency_placeholder = tf.placeholder(tf.float32, shape=())
# tf.summary.scalar('Execution Time', frequency_placeholder)
# TODO: support a d separate summary for metadata (e.g. execution time)
# Build the summary Tensor based on the TF collection of Summaries.
summary = tf.summary.merge_all()
# Add the variable initializer Op.
ivars = tf.global_variables() + tf.local_variables()
init = tf.variables_initializer(ivars)
# Create a saver for writing training checkpoints.
saver = tf.train.Saver()
# Create a logger to the validation accuracy
val_acc_pl = tf.placeholder(tf.float32, shape=())
summary_val_acc = tf.summary.scalar(name='validation_acc',
tensor=val_acc_pl,
collections=['validation'])
summary_val = tf.summary.merge([summary_val_acc])
# Create a session for running Ops on the Graph.
sess = tf.Session()
# Instantiate a SummaryWriter to output summaries and the Graph.
summary_writer_train = tf.summary.FileWriter(
os.path.join(FLAGS.log_dir, 'train'), sess.graph)
summary_writer_val = tf.summary.FileWriter(
os.path.join(FLAGS.log_dir, 'val'), sess.graph)
# And then after everything is built:
# Run the Op to initialize the variables.
sess.run(init)
# Start the training loop.
duration = 0
tp_value_total = 0
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, train_placeholder,
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, acc_val = sess.run([train_op, loss, eval_metric],
feed_dict=feed_dict)
duration += time.time() - start_time
tp_value_total += acc_val
# Write the summaries and print an overview fairly often.
if step % 100 == 0 and step > 0:
# Print status to stdout.
images_freq = 100 * FLAGS.batch_size / duration
print(
'Step %d: loss = %.2f, correct = %.2f%% (%.3f images/sec)'
% (step, loss_value, tp_value_total / FLAGS.batch_size,
images_freq))
duration = time.time() - start_time
tp_value_total = 0
duration = 0
# Update the events file.
summary_str = sess.run(summary, feed_dict=feed_dict)
summary_writer_train.add_summary(summary_str, step)
summary_writer_train.flush()
# Save a checkpoint and evaluate the model periodically.
if (step + 1) % 500 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_file = os.path.join(FLAGS.log_dir, 'model.ckpt')
saver.save(sess, checkpoint_file, global_step=step)
# Evaluate against the training set.
# print('Training Data Eval:')
# do_eval(sess,
# eval_metric,
# images_placeholder,
# labels_placeholder,
# train_placeholder,
# data_sets.train, summary)
# Evaluate against the validation set.
print('Validation Data Eval:')
accuracy_val = do_eval(sess, eval_metric, images_placeholder,
labels_placeholder, train_placeholder,
data_sets.validation)
# TODO: find a way to collect summaries for validation
summary_str = sess.run(summary_val,
feed_dict={val_acc_pl: accuracy_val})
summary_writer_val.add_summary(summary_str, step)
summary_writer_val.flush()
# Evaluate against the test set.
print('Test Data Eval:')
do_eval(sess, eval_metric, images_placeholder,
labels_placeholder, train_placeholder, data_sets.test)
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 tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
with tf.name_scope('Input'):
image_batch, label_batch = data_input.distorted_inputs(FLAGS.data_dir, 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(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)
# 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 = FLAGS.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(train_dir):
"""Loads the model and runs evaluation
"""
target_dir = os.path.join(train_dir, "model_files")
params = imp.load_source("params", os.path.join(target_dir, "params.py"))
data_input = imp.load_source("input", os.path.join(target_dir, "input.py"))
network = imp.load_source("network", os.path.join(target_dir,
"network.py"))
with tf.Graph().as_default():
# Retrieve images and labels
eval_data = FLAGS.eval_data == 'test'
images, labels = data_input.inputs(eval_data=eval_data,
data_dir=utils.cfg.data_dir,
batch_size=params.batch_size)
# Generate placeholders for the images and labels.
keep_prob = utils.placeholder_inputs(params.batch_size)
# Build a Graph that computes predictions from the inference model.
logits = network.inference(images, keep_prob)
# Add to the Graph the Ops for loss calculation.
loss = network.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 = network.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()
# 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)
ckpt = tf.train.get_checkpoint_state(train_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=params.num_examples_per_epoch_for_eval,
params=params,
name="eval")
