def slim_net_original(image, keep_prob):
with arg_scope([layers.conv2d, layers.fully_connected], biases_initializer=tf.random_normal_initializer(stddev=0.1)):
# conv2d(inputs, num_outputs, kernel_size, stride=1, padding='SAME',
# activation_fn=nn.relu, normalizer_fn=None, normalizer_params=None,
# weights_initializer=initializers.xavier_initializer(), weights_regularizer=None,
# biases_initializer=init_ops.zeros_initializer, biases_regularizer=None, scope=None):
net = layers.conv2d(image, 32, [5, 5], scope='conv1', weights_regularizer=regularizers.l1_regularizer(0.5))
# max_pool(inputs, kernel_size, stride=2, padding='VALID', scope=None)
net = layers.max_pool2d(net, 2, scope='pool1')
net = layers.conv2d(net, 64, [5, 5], scope='conv2', weights_regularizer=regularizers.l2_regularizer(0.5))
summaries.summarize_tensor(net, tag='conv2')
net = layers.max_pool2d(net, 2, scope='pool2')
net = layers.flatten(net, scope='flatten1')
# fully_connected(inputs, num_outputs, activation_fn=nn.relu, normalizer_fn=None,
# normalizer_params=None, weights_initializer=initializers.xavier_initializer(),
# weights_regularizer=None, biases_initializer=init_ops.zeros_initializer,
# biases_regularizer=None, scope=None):
net = layers.fully_connected(net, 1024, scope='fc1')
# dropout(inputs, keep_prob=0.5, is_training=True, scope=None)
net = layers.dropout(net, keep_prob=keep_prob, scope='dropout1')
net = layers.fully_connected(net, 10, scope='fc2')
return net
def slim_net_original(image, keep_prob):
with arg_scope(
[layers.conv2d, layers.fully_connected],
biases_initializer=tf.random_normal_initializer(stddev=0.1)):
# conv2d(inputs, num_outputs, kernel_size, stride=1, padding='SAME',
# activation_fn=nn.relu, normalizer_fn=None, normalizer_params=None,
# weights_initializer=initializers.xavier_initializer(), weights_regularizer=None,
# biases_initializer=init_ops.zeros_initializer, biases_regularizer=None, scope=None):
net = layers.conv2d(
image,
32, [5, 5],
scope='conv1',
weights_regularizer=regularizers.l1_regularizer(0.5))
# max_pool(inputs, kernel_size, stride=2, padding='VALID', scope=None)
net = layers.max_pool2d(net, 2, scope='pool1')
net = layers.conv2d(
net,
64, [5, 5],
scope='conv2',
weights_regularizer=regularizers.l2_regularizer(0.5))
summaries.summarize_tensor(net, tag='conv2')
net = layers.max_pool2d(net, 2, scope='pool2')
net = layers.flatten(net, scope='flatten1')
# fully_connected(inputs, num_outputs, activation_fn=nn.relu, normalizer_fn=None,
# normalizer_params=None, weights_initializer=initializers.xavier_initializer(),
# weights_regularizer=None, biases_initializer=init_ops.zeros_initializer,
# biases_regularizer=None, scope=None):
net = layers.fully_connected(net, 1024, scope='fc1')
# dropout(inputs, keep_prob=0.5, is_training=True, scope=None)
net = layers.dropout(net, keep_prob=keep_prob, scope='dropout1')
net = layers.fully_connected(net, 10, scope='fc2')
return net
def test_summarize_multidim_tensor(self):
with self.cached_session():
tensor_var = variables.Variable([1, 2, 3])
summary_op = summaries_lib.summarize_tensor(tensor_var)
self.assertEquals(summary_op.op.type, 'HistogramSummary')
def test_summarize_scalar_tensor(self):
with self.cached_session():
scalar_var = variables.Variable(1)
summary_op = summaries_lib.summarize_tensor(scalar_var)
self.assertEquals(summary_op.op.type, 'ScalarSummary')
def evaluate(graph,
output_dir,
checkpoint_path,
eval_dict,
update_op=None,
global_step_tensor=None,
supervisor_master='',
log_every_steps=10,
feed_fn=None,
max_steps=None):
"""Evaluate a model loaded from a checkpoint.
Given `graph`, a directory to write summaries to (`output_dir`), a checkpoint
to restore variables from, and a `dict` of `Tensor`s to evaluate, run an eval
loop for `max_steps` steps.
In each step of evaluation, all tensors in the `eval_dict` are evaluated, and
every `log_every_steps` steps, they are logged. At the very end of evaluation,
a summary is evaluated (finding the summary ops using `Supervisor`'s logic)
and written to `output_dir`.
Args:
graph: A `Graph` to train. It is expected that this graph is not in use
elsewhere.
output_dir: A string containing the directory to write a summary to.
checkpoint_path: A string containing the path to a checkpoint to restore.
Can be `None` if the graph doesn't require loading any variables.
eval_dict: A `dict` mapping string names to tensors to evaluate. It is
evaluated in every logging step. The result of the final evaluation is
returned. If update_op is None, then it's evaluated in every step.
update_op: A `Tensor` which is run in every step.
global_step_tensor: A `Variable` containing the global step. If `None`,
one is extracted from the graph using the same logic as in `Supervisor`.
Used to place eval summaries on training curves.
supervisor_master: The master string to use when preparing the session.
log_every_steps: Integer. Output logs every `log_every_steps` evaluation
steps. The logs contain the `eval_dict` and timing information.
feed_fn: A function that is called every iteration to produce a `feed_dict`
passed to `session.run` calls. Optional.
max_steps: Integer. Evaluate `eval_dict` this many times.
Returns:
A tuple `(eval_results, global_step)`:
eval_results: A `dict` mapping `string` to numeric values (`int`, `float`)
that are the result of running eval_dict in the last step. `None` if no
eval steps were run.
global_step: The global step this evaluation corresponds to.
"""
global_step_tensor = contrib_variables.assert_or_get_global_step(
graph, global_step_tensor)
# Add scalar summaries for every tensor in evaluation dict if there is not
# one existing already or it's a string.
existing_tags = [
tensor_util.constant_value(summary.op.inputs[0])
for summary in ops.get_collection(ops.GraphKeys.SUMMARIES)
]
for key, value in eval_dict.items():
if key in existing_tags:
continue
if isinstance(value, ops.Tensor):
summaries.summarize_tensor(value, tag=key)
# Create or get summary op, global_step and saver.
summary_op = logging_ops.get_summary_op()
saver = _get_saver()
local_init_op = _get_local_init_op()
ready_op = _get_ready_op()
session_manager = session_manager_lib.SessionManager(
local_init_op=local_init_op, ready_op=ready_op)
session, initialized = session_manager.recover_session(
master=supervisor_master, saver=saver, checkpoint_dir=checkpoint_path)
# Start queue runners.
coord = coordinator.Coordinator()
threads = _start_queue_runners(session, coord)
with session:
if not initialized:
logging.warning('Failed to initialize from %s.', checkpoint_path)
# TODO(ipolosukhin): This should be failing, but old code relies on that.
session.run(variables.initialize_all_variables())
if checkpoint_path:
_restore_from_checkpoint(session, graph, checkpoint_path,
saver)
current_global_step = session.run(global_step_tensor)
eval_results = None
# TODO(amodei): Fix this to run through the eval set exactly once.
step = 0
logging.info('Eval steps [%d,%s) for training step %d.', step,
'inf' if max_steps is None else str(max_steps),
current_global_step)
try:
try:
while (max_steps is None) or (step < max_steps):
start_time = time.time()
feed_dict = feed_fn() if feed_fn is not None else None
eval_results = None
if update_op is not None:
session.run(update_op, feed_dict=feed_dict)
else:
eval_results = _run_dict(session,
eval_dict,
feed_dict=feed_dict)
# TODO(wicke): We should assert that the global step hasn't changed.
step += 1
if step % log_every_steps == 0:
if eval_results is None:
eval_results = _run_dict(session,
eval_dict,
feed_dict=feed_dict)
duration = time.time() - start_time
logging.info(
'Results after %d steps (%.3f sec/batch): %s.',
step, float(duration),
', '.join('%s = %s' % (k, v)
for k, v in eval_results.items()))
finally:
if eval_results is None:
eval_results = _run_dict(session,
eval_dict,
feed_dict=feed_dict)
# Stop queue runners.
coord.request_stop()
coord.join(threads, stop_grace_period_secs=120)
# Make our own summary writer and write a summary to the eval dir.
# Only is feed_fn is not provided.
# TODO(ipolosukhin): Convert evaluation to use streaming_metrics,
# then we can save for non feed_fn as well.
if summary_op is not None and feed_fn is None:
summary_writer = None
try:
summary_writer = get_summary_writer(output_dir)
summary_str = session.run(summary_op)
if summary_str:
summary_writer.add_summary(summary_str,
current_global_step)
finally:
if summary_writer:
summary_writer.close()
# catch OutOfRangeError which is thrown when queue is out of data (and for
# other reasons as well).
except errors.OutOfRangeError as e:
if max_steps is None:
logging.info('Input queue is exhausted.')
else:
logging.warn('Input queue is exhausted: %s.', e)
# catch StopIteration which is thrown is DataReader is out of data.
except StopIteration as e:
if max_steps is None:
logging.info('Input iterator is exhausted.')
else:
logging.warn('Input iterator is exhausted: %s.', e)
return eval_results, current_global_step
# weights_regularizer=None, biases_initializer=init_ops.zeros_initializer,
# biases_regularizer=None, scope=None):
net = layers.fully_connected(net, 1024, scope='fc1')
# dropout(inputs, keep_prob=0.5, is_training=True, scope=None)
net = layers.dropout(net, keep_prob=keep_prob, scope='dropout1')
net = layers.fully_connected(net, 10, scope='fc2')
return net
y_pred = slim_net_original(tf.reshape(x, [-1, 28, 28, 1]), keep_prob)
with tf.name_scope('x_ent'):
cross_entropy = tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits(y_pred, y_true))
summaries.summarize_tensor(cross_entropy, tag='x_ent')
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y_true, 1))
accuracy = tf.reduce_mean(tf.to_float(correct_prediction))
summaries.summarize_tensor(accuracy, tag='acc')
sess = tf.Session()
merged = tf.merge_all_summaries()
writer = tf.train.SummaryWriter('/tmp/layers/run1', sess.graph)
sess.run(tf.initialize_all_variables())
def evaluate(graph,
output_dir,
checkpoint_path,
eval_dict,
global_step_tensor=None,
init_op=None,
supervisor_master='',
log_every_steps=10,
feed_fn=None,
max_steps=None):
"""Evaluate a model loaded from a checkpoint.
Given `graph`, a directory to write summaries to (`output_dir`), a checkpoint
to restore variables from, and a `dict` of `Tensor`s to evaluate, run an eval
loop for `max_steps` steps.
In each step of evaluation, all tensors in the `eval_dict` are evaluated, and
every `log_every_steps` steps, they are logged. At the very end of evaluation,
a summary is evaluated (finding the summary ops using `Supervisor`'s logic)
and written to `output_dir`.
Args:
graph: A `Graph` to train. It is expected that this graph is not in use
elsewhere.
output_dir: A string containing the directory to write a summary to.
checkpoint_path: A string containing the path to a checkpoint to restore.
Can be `None` if the graph doesn't require loading any variables.
eval_dict: A `dict` mapping string names to tensors to evaluate for in every
eval step.
global_step_tensor: A `Variable` containing the global step. If `None`,
one is extracted from the graph using the same logic as in `Supervisor`.
Used to place eval summaries on training curves.
init_op: An op that initializes the graph. If `None`, use `Supervisor`'s
default.
supervisor_master: The master string to use when preparing the session.
log_every_steps: Integer. Output logs every `log_every_steps` evaluation
steps. The logs contain the `eval_dict` and timing information.
feed_fn: A function that is called every iteration to produce a `feed_dict`
passed to `session.run` calls. Optional.
max_steps: Integer. Evaluate `eval_dict` this many times.
Returns:
A tuple `(eval_results, global_step)`:
eval_results: A `dict` mapping `string` to numeric values (`int`, `float`)
that are the eval results from the last step of the eval. None if no
eval steps were run.
global_step: The global step this evaluation corresponds to.
"""
global_step_tensor = contrib_variables.assert_or_get_global_step(
graph, global_step_tensor)
# Add scalar summaries for every tensor in evaluation dict if there is not
# one existing already or it's a string.
existing_tags = [
tensor_util.constant_value(summary.op.inputs[0])
for summary in ops.get_collection(ops.GraphKeys.SUMMARIES)
]
for key, value in eval_dict.items():
if key in existing_tags:
continue
if isinstance(value, ops.Tensor):
summaries.summarize_tensor(value, tag=key)
# Create or get summary op.
summary_op = logging_ops.get_summary_op()
# TODO(wicke): Don't use supervisor here, or switch to output_dir=eval_dir.
supervisor, session = _prepare_session(
graph=graph,
output_dir=None, # Must be None to avoid writing an event file
start_services=False,
global_step_tensor=global_step_tensor,
init_op=init_op,
supervisor_is_chief=True,
supervisor_master=supervisor_master,
supervisor_save_model_secs=None)
global_step_tensor = supervisor.global_step
with session:
if checkpoint_path:
_restore_from_checkpoint(session, graph, checkpoint_path,
supervisor.saver)
current_global_step = session.run(global_step_tensor)
eval_results = None
# TODO(amodei): Fix this to run through the eval set exactly once.
step = 0
logging.info('Eval steps [%d,%s)', step,
'inf' if max_steps is None else str(max_steps))
try:
try:
while not supervisor.ShouldStop() and ((max_steps is None) or
(step < max_steps)):
start_time = time.time()
feed_dict = feed_fn() if feed_fn is not None else None
eval_results = _run_dict(session,
eval_dict,
feed_dict=feed_dict)
# TODO(wicke): We should assert that the global step hasn't changed.
step += 1
if step % log_every_steps == 0:
duration = time.time() - start_time
logging.info(
'Results after %d steps (%.3f sec/batch): %s.',
step, float(duration),
', '.join('%s = %s' % (k, v)
for k, v in eval_results.items()))
finally:
# Make our own summary writer and write a summary to the eval dir.
# Only is feed_fn is not provided.
# TODO(ipolosukhin): Convert evaluation to use streaming_metrics,
# then we can save for non feed_fn as well.
if summary_op is not None and feed_fn is None:
summary_writer = None
try:
summary_writer = SummaryWriter(
output_dir, graph_def=session.graph_def)
summary_str = session.run(summary_op)
if summary_str:
summary_writer.add_summary(summary_str,
current_global_step)
finally:
if summary_writer:
summary_writer.close()
# Call supervisor.Stop() from within a try block because it re-raises
# exceptions thrown by the supervised threads.
supervisor.Stop()
# catch OutOfRangeError which is thrown when queue is out of data (and for
# other reasons as well).
except errors.OutOfRangeError as e:
logging.warn('Input queue is exhausted: %s.', e)
# catch StopIteration which is thrown is DataReader is out of data.
except StopIteration as e:
logging.info('Input iterator is exhausted: %s.', e)
return eval_results, current_global_step
def evaluate(graph,
output_dir,
checkpoint_path,
eval_dict,
update_op=None,
global_step_tensor=None,
supervisor_master='',
log_every_steps=10,
feed_fn=None,
max_steps=None):
"""Evaluate a model loaded from a checkpoint.
Given `graph`, a directory to write summaries to (`output_dir`), a checkpoint
to restore variables from, and a `dict` of `Tensor`s to evaluate, run an eval
loop for `max_steps` steps.
In each step of evaluation, all tensors in the `eval_dict` are evaluated, and
every `log_every_steps` steps, they are logged. At the very end of evaluation,
a summary is evaluated (finding the summary ops using `Supervisor`'s logic)
and written to `output_dir`.
Args:
graph: A `Graph` to train. It is expected that this graph is not in use
elsewhere.
output_dir: A string containing the directory to write a summary to.
checkpoint_path: A string containing the path to a checkpoint to restore.
Can be `None` if the graph doesn't require loading any variables.
eval_dict: A `dict` mapping string names to tensors to evaluate. It is
evaluated in every logging step. The result of the final evaluation is
returned. If update_op is None, then it's evaluated in every step.
update_op: A `Tensor` which is run in every step.
global_step_tensor: A `Variable` containing the global step. If `None`,
one is extracted from the graph using the same logic as in `Supervisor`.
Used to place eval summaries on training curves.
supervisor_master: The master string to use when preparing the session.
log_every_steps: Integer. Output logs every `log_every_steps` evaluation
steps. The logs contain the `eval_dict` and timing information.
feed_fn: A function that is called every iteration to produce a `feed_dict`
passed to `session.run` calls. Optional.
max_steps: Integer. Evaluate `eval_dict` this many times.
Returns:
A tuple `(eval_results, global_step)`:
eval_results: A `dict` mapping `string` to numeric values (`int`, `float`)
that are the result of running eval_dict in the last step. `None` if no
eval steps were run.
global_step: The global step this evaluation corresponds to.
"""
global_step_tensor = contrib_variables.assert_or_get_global_step(
graph, global_step_tensor)
# Add scalar summaries for every tensor in evaluation dict if there is not
# one existing already or it's a string.
existing_tags = [tensor_util.constant_value(summary.op.inputs[0])
for summary in ops.get_collection(ops.GraphKeys.SUMMARIES)]
for key, value in eval_dict.items():
if key in existing_tags:
continue
if isinstance(value, ops.Tensor):
summaries.summarize_tensor(value, tag=key)
# Create or get summary op, global_step and saver.
summary_op = logging_ops.get_summary_op()
saver = _get_saver()
local_init_op = _get_local_init_op()
ready_op = _get_ready_op()
session_manager = session_manager_lib.SessionManager(
local_init_op=local_init_op,
ready_op=ready_op)
session, initialized = session_manager.recover_session(
master=supervisor_master,
saver=saver,
checkpoint_dir=checkpoint_path)
# Start queue runners.
coord = coordinator.Coordinator()
threads = _start_queue_runners(session, coord)
with session:
if not initialized:
logging.warning('Failed to initialize from %s.', checkpoint_path)
# TODO(ipolosukhin): This should be failing, but old code relies on that.
session.run(variables.initialize_all_variables())
if checkpoint_path:
_restore_from_checkpoint(session, graph, checkpoint_path, saver)
current_global_step = session.run(global_step_tensor)
eval_results = None
# TODO(amodei): Fix this to run through the eval set exactly once.
step = 0
logging.info('Eval steps [%d,%s) for training step %d.', step,
'inf' if max_steps is None
else str(max_steps), current_global_step)
try:
try:
while (max_steps is None) or (step < max_steps):
start_time = time.time()
feed_dict = feed_fn() if feed_fn is not None else None
eval_results = None
if update_op is not None:
session.run(update_op, feed_dict=feed_dict)
else:
eval_results = _run_dict(session, eval_dict, feed_dict=feed_dict)
# TODO(wicke): We should assert that the global step hasn't changed.
step += 1
if step % log_every_steps == 0:
if eval_results is None:
eval_results = _run_dict(session, eval_dict, feed_dict=feed_dict)
duration = time.time() - start_time
logging.info('Results after %d steps (%.3f sec/batch): %s.',
step, float(duration),
', '.join('%s = %s' % (k, v)
for k, v in eval_results.items()))
finally:
if eval_results is None:
eval_results = _run_dict(session, eval_dict, feed_dict=feed_dict)
# Stop queue runners.
coord.request_stop()
coord.join(threads, stop_grace_period_secs=120)
# Make our own summary writer and write a summary to the eval dir.
# Only is feed_fn is not provided.
# TODO(ipolosukhin): Convert evaluation to use streaming_metrics,
# then we can save for non feed_fn as well.
if summary_op is not None and feed_fn is None:
summary_writer = None
try:
summary_writer = SummaryWriter(output_dir,
graph_def=session.graph_def)
summary_str = session.run(summary_op)
if summary_str:
summary_writer.add_summary(summary_str, current_global_step)
finally:
if summary_writer:
summary_writer.close()
# catch OutOfRangeError which is thrown when queue is out of data (and for
# other reasons as well).
except errors.OutOfRangeError as e:
if max_steps is None:
logging.info('Input queue is exhausted.')
else:
logging.warn('Input queue is exhausted: %s.', e)
# catch StopIteration which is thrown is DataReader is out of data.
except StopIteration as e:
if max_steps is None:
logging.info('Input iterator is exhausted.')
else:
logging.warn('Input iterator is exhausted: %s.', e)
return eval_results, current_global_step
def evaluate(graph,
output_dir,
checkpoint_path,
eval_dict,
global_step_tensor=None,
init_op=None,
supervisor_master='',
log_every_steps=10,
feed_fn=None,
max_steps=None):
"""Evaluate a model loaded from a checkpoint.
Given `graph`, a directory to write summaries to (`output_dir`), a checkpoint
to restore variables from, and a `dict` of `Tensor`s to evaluate, run an eval
loop for `max_steps` steps.
In each step of evaluation, all tensors in the `eval_dict` are evaluated, and
every `log_every_steps` steps, they are logged. At the very end of evaluation,
a summary is evaluated (finding the summary ops using `Supervisor`'s logic)
and written to `output_dir`.
Args:
graph: A `Graph` to train. It is expected that this graph is not in use
elsewhere.
output_dir: A string containing the directory to write a summary to.
checkpoint_path: A string containing the path to a checkpoint to restore.
Can be `None` if the graph doesn't require loading any variables.
eval_dict: A `dict` mapping string names to tensors to evaluate for in every
eval step.
global_step_tensor: A `Variable` containing the global step. If `None`,
one is extracted from the graph using the same logic as in `Supervisor`.
Used to place eval summaries on training curves.
init_op: An op that initializes the graph. If `None`, use `Supervisor`'s
default.
supervisor_master: The master string to use when preparing the session.
log_every_steps: Integer. Output logs every `log_every_steps` evaluation
steps. The logs contain the `eval_dict` and timing information.
feed_fn: A function that is called every iteration to produce a `feed_dict`
passed to `session.run` calls. Optional.
max_steps: Integer. Evaluate `eval_dict` this many times.
Returns:
A tuple `(eval_results, global_step)`:
eval_results: A `dict` mapping `string` to numeric values (`int`, `float`)
that are the eval results from the last step of the eval. None if no
eval steps were run.
global_step: The global step this evaluation corresponds to.
"""
global_step_tensor = contrib_variables.assert_or_get_global_step(
graph, global_step_tensor)
# Add scalar summaries for every tensor in evaluation dict if there is not
# one existing already or it's a string.
existing_tags = [tensor_util.constant_value(summary.op.inputs[0])
for summary in ops.get_collection(ops.GraphKeys.SUMMARIES)]
for key, value in eval_dict.items():
if key in existing_tags:
continue
if isinstance(value, ops.Tensor):
summaries.summarize_tensor(value, tag=key)
# TODO(wicke): Don't use supervisor here, or switch to output_dir=eval_dir.
supervisor, session = _prepare_session(
graph=graph,
output_dir=None, # Must be None to avoid writing an event file
start_services=False,
global_step_tensor=global_step_tensor,
init_op=init_op,
supervisor_is_chief=True,
supervisor_master=supervisor_master,
supervisor_save_model_secs=None,
supervisor_save_summaries_secs=None)
global_step_tensor = supervisor.global_step
with session:
if checkpoint_path:
_restore_from_checkpoint(
session, graph, checkpoint_path, supervisor.saver)
current_global_step = session.run(global_step_tensor)
eval_results = None
# TODO(amodei): Fix this to run through the eval set exactly once.
step = 0
logging.info('Eval steps [%d,%s)', step, 'inf' if max_steps is None
else str(max_steps))
try:
try:
while not supervisor.ShouldStop() and (
(max_steps is None) or (step < max_steps)):
start_time = time.time()
feed_dict = feed_fn() if feed_fn is not None else None
eval_results = _run_dict(session, eval_dict, feed_dict=feed_dict)
# TODO(wicke): We should assert that the global step hasn't changed.
step += 1
if step % log_every_steps == 0:
duration = time.time() - start_time
logging.info('Results after %d steps (%.3f sec/batch): %s.',
step, float(duration),
', '.join('%s = %s' % (k, v)
for k, v in eval_results.items()))
finally:
# Make our own summary writer and write a summary to the eval dir
if supervisor.summary_op is not None:
summary_writer = None
try:
summary_writer = SummaryWriter(output_dir,
graph_def=session.graph_def)
summary_str = session.run(supervisor.summary_op)
if summary_str:
summary_writer.add_summary(summary_str, current_global_step)
finally:
if summary_writer:
summary_writer.close()
# Call supervisor.Stop() from within a try block because it re-raises
# exceptions thrown by the supervised threads.
supervisor.Stop()
# catch OutOfRangeError which is thrown when queue is out of data (and for
# other reasons as well).
except errors.OutOfRangeError as e:
logging.warn('Input queue exhausted: %s.', e)
return eval_results, current_global_step
# biases_regularizer=None, scope=None):
net = layers.fully_connected(net, 1024, scope='fc1')
# dropout(inputs, keep_prob=0.5, is_training=True, scope=None)
net = layers.dropout(net, keep_prob=keep_prob, scope='dropout1')
net = layers.fully_connected(net, 10, scope='fc2')
return net
y_pred = slim_net_original(tf.reshape(x, [-1, 28, 28, 1]), keep_prob)
with tf.name_scope('x_ent'):
cross_entropy = tf.reduce_sum(
tf.nn.softmax_cross_entropy_with_logits(y_pred, y_true))
summaries.summarize_tensor(cross_entropy, tag='x_ent')
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y_true, 1))
accuracy = tf.reduce_mean(tf.to_float(correct_prediction))
summaries.summarize_tensor(accuracy, tag='acc')
sess = tf.Session()
merged = tf.merge_all_summaries()
writer = tf.train.SummaryWriter('/tmp/layers/run1', sess.graph)
sess.run(tf.initialize_all_variables())
