def testNewClassificationLocalizationWeightRatio(self):
"""Tests that the loss weight ratio is updated appropriately."""
original_localization_weight = 0.1
original_classification_weight = 0.2
new_weight_ratio = 5.0
hparams = tf.contrib.training.HParams(
classification_localization_weight_ratio=new_weight_ratio)
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.model.faster_rcnn.first_stage_localization_loss_weight = (
original_localization_weight)
pipeline_config.model.faster_rcnn.second_stage_classification_loss_weight = (
original_classification_weight)
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
loss = configs["model"].faster_rcnn
self.assertAlmostEqual(1.0, loss.first_stage_localization_loss_weight)
self.assertAlmostEqual(new_weight_ratio,
loss.second_stage_classification_loss_weight)
#def testNewFocalLossParameters(self):
"""Tests that the loss weight ratio is updated appropriately.
def test_get_configs_from_pipeline_file(self):
"""Test that proto configs can be read from pipeline config file."""
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.model.faster_rcnn.num_classes = 10
pipeline_config.train_config.batch_size = 32
pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
pipeline_config.eval_config.num_examples = 20
pipeline_config.eval_input_reader.queue_capacity = 100
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
self.assertProtoEquals(pipeline_config.model, configs["model"])
self.assertProtoEquals(pipeline_config.train_config,
configs["train_config"])
self.assertProtoEquals(pipeline_config.train_input_reader,
configs["train_input_config"])
self.assertProtoEquals(pipeline_config.eval_config,
configs["eval_config"])
self.assertProtoEquals(pipeline_config.eval_input_reader,
configs["eval_input_config"])
def main(unused_argv):
assert FLAGS.checkpoint_dir, '`checkpoint_dir` is missing.'
assert FLAGS.eval_dir, '`eval_dir` is missing.'
tf.gfile.MakeDirs(FLAGS.eval_dir)
if FLAGS.pipeline_config_path:
configs = config_util.get_configs_from_pipeline_file(
FLAGS.pipeline_config_path)
tf.gfile.Copy(FLAGS.pipeline_config_path,
os.path.join(FLAGS.eval_dir, 'pipeline.config'),
overwrite=True)
else:
configs = config_util.get_configs_from_multiple_files(
model_config_path=FLAGS.model_config_path,
eval_config_path=FLAGS.eval_config_path,
eval_input_config_path=FLAGS.input_config_path)
for name, config in [('model.config', FLAGS.model_config_path),
('eval.config', FLAGS.eval_config_path),
('input.config', FLAGS.input_config_path)]:
tf.gfile.Copy(config,
os.path.join(FLAGS.eval_dir, name),
overwrite=True)
model_config = configs['model']
eval_config = configs['eval_config']
input_config = configs['eval_input_config']
if FLAGS.eval_training_data:
input_config = configs['train_input_config']
model_fn = functools.partial(model_builder.build,
model_config=model_config,
is_training=False)
def get_next(config):
return dataset_builder.make_initializable_iterator(
dataset_builder.build(config)).get_next()
create_input_dict_fn = functools.partial(get_next, input_config)
label_map = label_map_util.load_labelmap(input_config.label_map_path)
max_num_classes = max([item.id for item in label_map.item])
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes)
if FLAGS.run_once:
eval_config.max_evals = 1
graph_rewriter_fn = None
if 'graph_rewriter_config' in configs:
graph_rewriter_fn = graph_rewriter_builder.build(
configs['graph_rewriter_config'], is_training=False)
evaluator.evaluate(create_input_dict_fn,
model_fn,
eval_config,
categories,
FLAGS.checkpoint_dir,
FLAGS.eval_dir,
graph_hook_fn=graph_rewriter_fn)
def testGetNumberOfClasses(self):
"""Tests that number of classes can be retrieved."""
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.model.faster_rcnn.num_classes = 20
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
number_of_classes = config_util.get_number_of_classes(configs["model"])
self.assertEqual(20, number_of_classes)
def testUseMovingAverageForEval(self):
use_moving_averages_orig = False
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.eval_config.use_moving_averages = use_moving_averages_orig
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, eval_with_moving_averages=True)
self.assertEqual(True, configs["eval_config"].use_moving_averages)
def test_save_pipeline_config(self):
"""Tests that the pipeline config is properly saved to disk."""
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.model.faster_rcnn.num_classes = 10
pipeline_config.train_config.batch_size = 32
pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
pipeline_config.eval_config.num_examples = 20
pipeline_config.eval_input_reader.queue_capacity = 100
config_util.save_pipeline_config(pipeline_config, self.get_temp_dir())
configs = config_util.get_configs_from_pipeline_file(
os.path.join(self.get_temp_dir(), "pipeline.config"))
pipeline_config_reconstructed = (
config_util.create_pipeline_proto_from_configs(configs))
self.assertEqual(pipeline_config, pipeline_config_reconstructed)
def testNewBatchSizeWithClipping(self):
"""Tests that batch size is clipped to 1 from below."""
original_batch_size = 2
hparams = tf.contrib.training.HParams(batch_size=0.5)
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.train_config.batch_size = original_batch_size
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
new_batch_size = configs["train_config"].batch_size
self.assertEqual(1, new_batch_size) # Clipped to 1.0.
def testNewBatchSize(self):
"""Tests that batch size is updated appropriately."""
original_batch_size = 2
hparams = tf.contrib.training.HParams(batch_size=16)
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.train_config.batch_size = original_batch_size
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
new_batch_size = configs["train_config"].batch_size
self.assertEqual(16, new_batch_size)
def test_create_pipeline_proto_from_configs(self):
"""Tests that proto can be reconstructed from configs dictionary."""
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.model.faster_rcnn.num_classes = 10
pipeline_config.train_config.batch_size = 32
pipeline_config.train_input_reader.label_map_path = "path/to/label_map"
pipeline_config.eval_config.num_examples = 20
pipeline_config.eval_input_reader.queue_capacity = 100
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
pipeline_config_reconstructed = (
config_util.create_pipeline_proto_from_configs(configs))
self.assertEqual(pipeline_config, pipeline_config_reconstructed)
def testNewTrainInputPathList(self):
"""Tests that train input path can be overwritten with multiple files."""
original_train_path = ["path/to/data"]
new_train_path = ["another/path/to/data", "yet/another/path/to/data"]
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
reader_config = pipeline_config.train_input_reader.tf_record_input_reader
reader_config.input_path.extend(original_train_path)
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, train_input_path=new_train_path)
reader_config = configs["train_input_config"].tf_record_input_reader
final_path = reader_config.input_path
self.assertEqual(new_train_path, final_path)
def testNewMomentumOptimizerValue(self):
"""Tests that new momentum value is updated appropriately."""
original_momentum_value = 0.4
hparams = tf.contrib.training.HParams(momentum_optimizer_value=1.1)
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
optimizer_config = pipeline_config.train_config.optimizer.rms_prop_optimizer
optimizer_config.momentum_optimizer_value = original_momentum_value
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
optimizer_config = configs["train_config"].optimizer.rms_prop_optimizer
new_momentum_value = optimizer_config.momentum_optimizer_value
self.assertAlmostEqual(1.0, new_momentum_value) # Clipped to 1.0.
def testNewMaskType(self):
"""Tests that mask type can be overwritten in input readers."""
original_mask_type = input_reader_pb2.NUMERICAL_MASKS
new_mask_type = input_reader_pb2.PNG_MASKS
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
train_input_reader = pipeline_config.train_input_reader
train_input_reader.mask_type = original_mask_type
eval_input_reader = pipeline_config.eval_input_reader
eval_input_reader.mask_type = original_mask_type
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, mask_type=new_mask_type)
self.assertEqual(new_mask_type,
configs["train_input_config"].mask_type)
self.assertEqual(new_mask_type, configs["eval_input_config"].mask_type)
def testDontOverwriteEmptyLabelMapPath(self):
"""Tests that label map path will not by overwritten with empty string."""
original_label_map_path = "path/to/original/label_map"
new_label_map_path = ""
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
train_input_reader = pipeline_config.train_input_reader
train_input_reader.label_map_path = original_label_map_path
eval_input_reader = pipeline_config.eval_input_reader
eval_input_reader.label_map_path = original_label_map_path
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, label_map_path=new_label_map_path)
self.assertEqual(original_label_map_path,
configs["train_input_config"].label_map_path)
self.assertEqual(original_label_map_path,
configs["eval_input_config"].label_map_path)
def testMergingKeywordArguments(self):
"""Tests that keyword arguments get merged as do hyperparameters."""
original_num_train_steps = 100
original_num_eval_steps = 5
desired_num_train_steps = 10
desired_num_eval_steps = 1
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
pipeline_config.train_config.num_steps = original_num_train_steps
pipeline_config.eval_config.num_examples = original_num_eval_steps
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs,
train_steps=desired_num_train_steps,
eval_steps=desired_num_eval_steps)
train_steps = configs["train_config"].num_steps
eval_steps = configs["eval_config"].num_examples
self.assertEqual(desired_num_train_steps, train_steps)
self.assertEqual(desired_num_eval_steps, eval_steps)
def _assertOptimizerWithNewLearningRate(self, optimizer_name):
"""Asserts successful updating of all learning rate schemes."""
original_learning_rate = 0.7
learning_rate_scaling = 0.1
warmup_learning_rate = 0.07
hparams = tf.contrib.training.HParams(learning_rate=0.15)
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
# Constant learning rate.
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
optimizer = getattr(pipeline_config.train_config.optimizer,
optimizer_name)
_update_optimizer_with_constant_learning_rate(optimizer,
original_learning_rate)
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
optimizer = getattr(configs["train_config"].optimizer, optimizer_name)
constant_lr = optimizer.learning_rate.constant_learning_rate
self.assertAlmostEqual(hparams.learning_rate,
constant_lr.learning_rate)
# Exponential decay learning rate.
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
optimizer = getattr(pipeline_config.train_config.optimizer,
optimizer_name)
_update_optimizer_with_exponential_decay_learning_rate(
optimizer, original_learning_rate)
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
optimizer = getattr(configs["train_config"].optimizer, optimizer_name)
exponential_lr = optimizer.learning_rate.exponential_decay_learning_rate
self.assertAlmostEqual(hparams.learning_rate,
exponential_lr.initial_learning_rate)
# Manual step learning rate.
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
optimizer = getattr(pipeline_config.train_config.optimizer,
optimizer_name)
_update_optimizer_with_manual_step_learning_rate(
optimizer, original_learning_rate, learning_rate_scaling)
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
optimizer = getattr(configs["train_config"].optimizer, optimizer_name)
manual_lr = optimizer.learning_rate.manual_step_learning_rate
self.assertAlmostEqual(hparams.learning_rate,
manual_lr.initial_learning_rate)
for i, schedule in enumerate(manual_lr.schedule):
self.assertAlmostEqual(
hparams.learning_rate * learning_rate_scaling**i,
schedule.learning_rate)
# Cosine decay learning rate.
pipeline_config = pipeline_pb2.TrainEvalPipelineConfig()
optimizer = getattr(pipeline_config.train_config.optimizer,
optimizer_name)
_update_optimizer_with_cosine_decay_learning_rate(
optimizer, original_learning_rate, warmup_learning_rate)
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(
pipeline_config_path)
configs = config_util.merge_external_params_with_configs(
configs, hparams)
optimizer = getattr(configs["train_config"].optimizer, optimizer_name)
cosine_lr = optimizer.learning_rate.cosine_decay_learning_rate
self.assertAlmostEqual(hparams.learning_rate,
cosine_lr.learning_rate_base)
warmup_scale_factor = warmup_learning_rate / original_learning_rate
self.assertAlmostEqual(hparams.learning_rate * warmup_scale_factor,
cosine_lr.warmup_learning_rate)
def main(_):
assert FLAGS.train_dir, '`train_dir` is missing.'
if FLAGS.task == 0: tf.gfile.MakeDirs(FLAGS.train_dir)
if FLAGS.pipeline_config_path:
configs = config_util.get_configs_from_pipeline_file(
FLAGS.pipeline_config_path)
if FLAGS.task == 0:
tf.gfile.Copy(FLAGS.pipeline_config_path,
os.path.join(FLAGS.train_dir, 'pipeline.config'),
overwrite=True)
else:
configs = config_util.get_configs_from_multiple_files(
model_config_path=FLAGS.model_config_path,
train_config_path=FLAGS.train_config_path,
train_input_config_path=FLAGS.input_config_path)
if FLAGS.task == 0:
for name, config in [('model.config', FLAGS.model_config_path),
('train.config', FLAGS.train_config_path),
('input.config', FLAGS.input_config_path)]:
tf.gfile.Copy(config, os.path.join(FLAGS.train_dir, name),
overwrite=True)
model_config = configs['model']
train_config = configs['train_config']
input_config = configs['train_input_config']
model_fn = functools.partial(
model_builder.build,
model_config=model_config,
is_training=True)
def get_next(config):
return dataset_util.make_initializable_iterator(
dataset_builder.build(config)).get_next()
create_input_dict_fn = functools.partial(get_next, input_config)
env = json.loads(os.environ.get('TF_CONFIG', '{}'))
cluster_data = env.get('cluster', None)
cluster = tf.train.ClusterSpec(cluster_data) if cluster_data else None
task_data = env.get('task', None) or {'type': 'master', 'index': 0}
task_info = type('TaskSpec', (object,), task_data)
# Parameters for a single worker.
ps_tasks = 0
worker_replicas = 1
worker_job_name = 'lonely_worker'
task = 0
is_chief = True
master = ''
if cluster_data and 'worker' in cluster_data:
# Number of total worker replicas include "worker"s and the "master".
worker_replicas = len(cluster_data['worker']) + 1
if cluster_data and 'ps' in cluster_data:
ps_tasks = len(cluster_data['ps'])
if worker_replicas > 1 and ps_tasks < 1:
raise ValueError('At least 1 ps task is needed for distributed training.')
if worker_replicas >= 1 and ps_tasks > 0:
# Set up distributed training.
server = tf.train.Server(tf.train.ClusterSpec(cluster), protocol='grpc',
job_name=task_info.type,
task_index=task_info.index)
if task_info.type == 'ps':
server.join()
return
worker_job_name = '%s/task:%d' % (task_info.type, task_info.index)
task = task_info.index
is_chief = (task_info.type == 'master')
master = server.target
graph_rewriter_fn = None
if 'graph_rewriter_config' in configs:
graph_rewriter_fn = graph_rewriter_builder.build(
configs['graph_rewriter_config'], is_training=True)
trainer.train(
create_input_dict_fn,
model_fn,
train_config,
master,
task,
FLAGS.num_clones,
worker_replicas,
FLAGS.clone_on_cpu,
ps_tasks,
worker_job_name,
is_chief,
FLAGS.train_dir,
graph_hook_fn=graph_rewriter_fn)
def _create_and_load_test_configs(self, pipeline_config):
pipeline_config_path = os.path.join(self.get_temp_dir(),
"pipeline.config")
_write_config(pipeline_config, pipeline_config_path)
return config_util.get_configs_from_pipeline_file(pipeline_config_path)
