def transform_and_pad_input_data_fn(tensor_dict):
"""Combines transform and pad operation."""
num_classes = config_util.get_number_of_classes(model_config)
image_resizer_config = config_util.get_image_resizer_config(
model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
keypoint_type_weight = eval_input_config.keypoint_type_weight or None
transform_data_fn = functools.partial(
transform_input_data,
model_preprocess_fn=model_preprocess_fn,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None,
retain_original_image=eval_config.retain_original_images,
retain_original_image_additional_channels=eval_config.
retain_original_image_additional_channels,
keypoint_type_weight=keypoint_type_weight)
tensor_dict = pad_input_data_to_static_shapes(
tensor_dict=transform_data_fn(tensor_dict),
max_num_boxes=eval_input_config.max_number_of_boxes,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config),
max_num_context_features=config_util.get_max_num_context_features(
model_config),
context_feature_length=config_util.get_context_feature_length(
model_config))
return (_get_features_dict(tensor_dict), _get_labels_dict(tensor_dict))
def transform_and_pad_input_data_fn(tensor_dict):
"""Combines transform and pad operation."""
data_augmentation_options = [
preprocessor_builder.build(step)
for step in train_config.data_augmentation_options
]
data_augmentation_fn = functools.partial(
augment_input_data,
data_augmentation_options=data_augmentation_options)
model = model_builder.build(model_config, is_training=True)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data, model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=config_util.get_number_of_classes(model_config),
data_augmentation_fn=data_augmentation_fn,
merge_multiple_boxes=train_config.merge_multiple_label_boxes,
retain_original_image=train_config.retain_original_images,
use_bfloat16=train_config.use_bfloat16)
tensor_dict = pad_input_data_to_static_shapes(
tensor_dict=transform_data_fn(tensor_dict),
max_num_boxes=train_input_config.max_number_of_boxes,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
return (_get_features_dict(tensor_dict), _get_labels_dict(tensor_dict))
def transform_and_pad_input_data_fn(tensor_dict):
"""Combines transform and pad operation."""
data_augmentation_options = [
preprocessor_builder.build(step)
for step in train_config.data_augmentation_options
]
data_augmentation_fn = functools.partial(
augment_input_data,
data_augmentation_options=data_augmentation_options)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data, model_preprocess_fn=model_preprocess_fn,
image_resizer_fn=image_resizer_fn,
num_classes=config_util.get_number_of_classes(model_config),
data_augmentation_fn=data_augmentation_fn,
merge_multiple_boxes=train_config.merge_multiple_label_boxes,
retain_original_image=train_config.retain_original_images,
use_multiclass_scores=train_config.use_multiclass_scores,
use_bfloat16=train_config.use_bfloat16)
tensor_dict = pad_input_data_to_static_shapes(
tensor_dict=transform_data_fn(tensor_dict),
max_num_boxes=train_input_config.max_number_of_boxes,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
return (_get_features_dict(tensor_dict), _get_labels_dict(tensor_dict))
def testUpdateNumClasses(self):
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
_write_config(pipeline_config, pipeline_config_path)
configs = config_util.get_configs_from_pipeline_file(pipeline_config_path)
self.assertEqual(config_util.get_number_of_classes(configs["model"]), 10)
config_util.merge_external_params_with_configs(
configs, kwargs_dict={"num_classes": 2})
self.assertEqual(config_util.get_number_of_classes(configs["model"]), 2)
def _predict_input_fn(params=None):
"""Decodes serialized tf.Examples and returns `ServingInputReceiver`.
Args:
params: Parameter dictionary passed from the estimator.
Returns:
`ServingInputReceiver`.
"""
del params
example = tf.placeholder(dtype=tf.string, shape=[], name='input_feature')
num_classes = config_util.get_number_of_classes(model_config)
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_fn = functools.partial(
transform_input_data, model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None)
decoder = tf_example_decoder.TfExampleDecoder(load_instance_masks=False)
input_dict = transform_fn(decoder.decode(example))
images = tf.to_float(input_dict[fields.InputDataFields.image])
images = tf.expand_dims(images, axis=0)
return tf.estimator.export.ServingInputReceiver(
features={fields.InputDataFields.image: images},
receiver_tensors={SERVING_FED_EXAMPLE_KEY: example})
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 transform_and_pad_input_data_fn(tensor_dict):
"""Combines transform and pad operation."""
num_classes = config_util.get_number_of_classes(model_config)
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data, model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None,
retain_original_image=eval_config.retain_original_images)
tensor_dict = pad_input_data_to_static_shapes(
tensor_dict=transform_data_fn(tensor_dict),
max_num_boxes=eval_input_config.max_number_of_boxes,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
return (_get_features_dict(tensor_dict), _get_labels_dict(tensor_dict))
def transform_and_pad_input_data_fn(tensor_dict):
"""Combines transform and pad operation."""
num_classes = config_util.get_number_of_classes(model_config)
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data, model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None,
retain_original_image=eval_config.retain_original_images)
tensor_dict = pad_input_data_to_static_shapes(
tensor_dict=transform_data_fn(tensor_dict),
max_num_boxes=eval_input_config.max_number_of_boxes,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
return (_get_features_dict(tensor_dict), _get_labels_dict(tensor_dict))
def transform_and_pad_input_data_fn(tensor_dict):
"""Combines transform and pad operation."""
model = model_builder.build(model_config, is_training=True)
image_resizer_config = config_util.get_image_resizer_config(
model_config)
image_resizer_fn = image_resizer_builder.build(
image_resizer_config)
if is_training:
data_augmentation_options = [
preprocessor_builder.build(step)
for step in train_config.data_augmentation_options
]
data_augmentation_fn = functools.partial(
augment_input_data,
data_augmentation_options=data_augmentation_options)
transform_data_fn = functools.partial(
transform_input_data,
model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=config_util.get_number_of_classes(
model_config),
data_augmentation_fn=data_augmentation_fn,
merge_multiple_boxes=train_config.
merge_multiple_label_boxes,
retain_original_image=train_config.retain_original_images)
else:
transform_data_fn = functools.partial(
transform_input_data,
model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=config_util.get_number_of_classes(
model_config),
data_augmentation_fn=None,
retain_original_image=train_config.retain_original_images)
tensor_dict = transform_data_fn(tensor_dict)
return (_get_features_dict(tensor_dict),
_get_labels_dict(tensor_dict))
def _predict_input_fn(params=None):
"""Decodes serialized tf.Examples and returns `ServingInputReceiver`.
Args:
params: Parameter dictionary passed from the estimator.
Returns:
`ServingInputReceiver`.
"""
del params
example = tf.placeholder(dtype=tf.string, shape=[], name='tf_example')
num_classes = config_util.get_number_of_classes(model_config)
model_preprocess_fn = INPUT_BUILDER_UTIL_MAP['model_build'](
model_config, is_training=False).preprocess
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_fn = functools.partial(
transform_input_data, model_preprocess_fn=model_preprocess_fn,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None)
decoder = tf_multi_layer_decoder.TfMultiLayerDecoder(
['x_c', 'y_c', 'w', 'h', 'sin_angle', 'cos_angle'],
input_features=model_config.input_features,
input_channels=model_config.input_channels)
# ,num_additional_channels=predict_input_config.num_additional_channels)
input_dict = transform_fn(decoder.decode(example))
images = tf.cast(input_dict[fields.InputDataFields.image], dtype=tf.float32)
images = tf.expand_dims(images, axis=0)
true_image_shape = tf.expand_dims(
input_dict[fields.InputDataFields.true_image_shape], axis=0)
return tf.estimator.export.ServingInputReceiver(
features={
fields.InputDataFields.image: images,
fields.InputDataFields.true_image_shape: true_image_shape},
receiver_tensors={SERVING_FED_EXAMPLE_KEY: example})
def _predict_input_fn(params=None):
del params
example = tf.placeholder(dtype=tf.string, shape=[], name='tf_example')
num_classes = config_util.get_number_of_classes(model_config)
model_preprocess_fn = INPUT_BUILDER_UTIL_MAP['model_build'](
model_config, is_training=False).preprocess
image_resizer_config = config_util.get_image_resizer_config(
model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_fn = functools.partial(
transform_input_data,
model_preprocess_fn=model_preprocess_fn,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None)
decoder = tf_example_decoder.TfExampleDecoder(
load_instance_masks=False,
num_additional_channels=predict_input_config.
num_additional_channels)
input_dict = transform_fn(decoder.decode(example))
images = tf.cast(input_dict[fields.InputDataFields.image],
dtype=tf.float32)
images = tf.expand_dims(images, axis=0)
true_image_shape = tf.expand_dims(
input_dict[fields.InputDataFields.true_image_shape], axis=0)
return tf.estimator.export.ServingInputReceiver(
features={
fields.InputDataFields.image: images,
fields.InputDataFields.true_image_shape: true_image_shape
},
receiver_tensors={SERVING_FED_EXAMPLE_KEY: example})
def _eval_input_fn(params=None):
"""Returns `features` and `labels` tensor dictionaries for evaluation.
Args:
params: Parameter dictionary passed from the estimator.
Returns:
features: Dictionary of feature tensors.
features[fields.InputDataFields.image] is a [1, H, W, C] float32 tensor
with preprocessed images.
features[HASH_KEY] is a [1] int32 tensor representing unique
identifiers for the images.
features[fields.InputDataFields.true_image_shape] is a [1, 3]
int32 tensor representing the true image shapes, as preprocessed
images could be padded.
features[fields.InputDataFields.original_image] is a [1, H', W', C]
float32 tensor with the original image.
labels: Dictionary of groundtruth tensors.
labels[fields.InputDataFields.groundtruth_boxes] is a [1, num_boxes, 4]
float32 tensor containing the corners of the groundtruth boxes.
labels[fields.InputDataFields.groundtruth_classes] is a
[num_boxes, num_classes] float32 one-hot tensor of classes.
labels[fields.InputDataFields.groundtruth_area] is a [1, num_boxes]
float32 tensor containing object areas.
labels[fields.InputDataFields.groundtruth_is_crowd] is a [1, num_boxes]
bool tensor indicating if the boxes enclose a crowd.
labels[fields.InputDataFields.groundtruth_difficult] is a [1, num_boxes]
int32 tensor indicating if the boxes represent difficult instances.
-- Optional --
labels[fields.InputDataFields.groundtruth_instance_masks] is a
[1, num_boxes, H, W] float32 tensor containing only binary values,
which represent instance masks for objects.
Raises:
TypeError: if the `eval_config`, `eval_input_config` or `model_config`
are not of the correct type.
"""
del params
if not isinstance(eval_config, eval_pb2.EvalConfig):
raise TypeError('For eval mode, the `eval_config` must be a '
'train_pb2.EvalConfig.')
if not isinstance(eval_input_config, input_reader_pb2.InputReader):
raise TypeError('The `eval_input_config` must be a '
'input_reader_pb2.InputReader.')
if not isinstance(model_config, model_pb2.DetectionModel):
raise TypeError('The `model_config` must be a '
'model_pb2.DetectionModel.')
num_classes = config_util.get_number_of_classes(model_config)
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_util.get_image_resizer_config(
model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data,
model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None,
retain_original_image=eval_config.retain_original_images)
dataset = INPUT_BUILDER_UTIL_MAP['dataset_build'](
eval_input_config,
transform_input_data_fn=transform_data_fn,
batch_size=1,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
input_dict = dataset_util.make_initializable_iterator(
dataset).get_next()
return (_get_features_dict(input_dict), _get_labels_dict(input_dict))
def _train_input_fn(params=None):
"""Returns `features` and `labels` tensor dictionaries for training.
Args:
params: Parameter dictionary passed from the estimator.
Returns:
features: Dictionary of feature tensors.
features[fields.InputDataFields.image] is a [batch_size, H, W, C]
float32 tensor with preprocessed images.
features[HASH_KEY] is a [batch_size] int32 tensor representing unique
identifiers for the images.
features[fields.InputDataFields.true_image_shape] is a [batch_size, 3]
int32 tensor representing the true image shapes, as preprocessed
images could be padded.
features[fields.InputDataFields.original_image] (optional) is a
[batch_size, H, W, C] float32 tensor with original images.
labels: Dictionary of groundtruth tensors.
labels[fields.InputDataFields.num_groundtruth_boxes] is a [batch_size]
int32 tensor indicating the number of groundtruth boxes.
labels[fields.InputDataFields.groundtruth_boxes] is a
[batch_size, num_boxes, 4] float32 tensor containing the corners of
the groundtruth boxes.
labels[fields.InputDataFields.groundtruth_classes] is a
[batch_size, num_boxes, num_classes] float32 one-hot tensor of
classes.
labels[fields.InputDataFields.groundtruth_weights] is a
[batch_size, num_boxes] float32 tensor containing groundtruth weights
for the boxes.
-- Optional --
labels[fields.InputDataFields.groundtruth_instance_masks] is a
[batch_size, num_boxes, H, W] float32 tensor containing only binary
values, which represent instance masks for objects.
labels[fields.InputDataFields.groundtruth_keypoints] is a
[batch_size, num_boxes, num_keypoints, 2] float32 tensor containing
keypoints for each box.
Raises:
TypeError: if the `train_config`, `train_input_config` or `model_config`
are not of the correct type.
"""
if not isinstance(train_config, train_pb2.TrainConfig):
raise TypeError('For training mode, the `train_config` must be a '
'train_pb2.TrainConfig.')
if not isinstance(train_input_config, input_reader_pb2.InputReader):
raise TypeError('The `train_input_config` must be a '
'input_reader_pb2.InputReader.')
if not isinstance(model_config, model_pb2.DetectionModel):
raise TypeError('The `model_config` must be a '
'model_pb2.DetectionModel.')
data_augmentation_options = [
preprocessor_builder.build(step)
for step in train_config.data_augmentation_options
]
data_augmentation_fn = functools.partial(
augment_input_data,
data_augmentation_options=data_augmentation_options)
model = model_builder.build(model_config, is_training=True)
image_resizer_config = config_util.get_image_resizer_config(
model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data,
model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=config_util.get_number_of_classes(model_config),
data_augmentation_fn=data_augmentation_fn,
retain_original_image=train_config.retain_original_images)
dataset = INPUT_BUILDER_UTIL_MAP['dataset_build'](
train_input_config,
transform_input_data_fn=transform_data_fn,
batch_size=params['batch_size']
if params else train_config.batch_size,
max_num_boxes=train_config.max_number_of_boxes,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
input_dict = dataset_util.make_initializable_iterator(
dataset).get_next()
return (_get_features_dict(input_dict), _get_labels_dict(input_dict))
def _eval_input_fn(params=None):
"""Returns `features` and `labels` tensor dictionaries for evaluation.
Args:
params: Parameter dictionary passed from the estimator.
Returns:
features: Dictionary of feature tensors.
features[fields.InputDataFields.image] is a [1, H, W, C] float32 tensor
with preprocessed images.
features[HASH_KEY] is a [1] int32 tensor representing unique
identifiers for the images.
features[fields.InputDataFields.true_image_shape] is a [1, 3]
int32 tensor representing the true image shapes, as preprocessed
images could be padded.
features[fields.InputDataFields.original_image] is a [1, H', W', C]
float32 tensor with the original image.
labels: Dictionary of groundtruth tensors.
labels[fields.InputDataFields.groundtruth_boxes] is a [1, num_boxes, 4]
float32 tensor containing the corners of the groundtruth boxes.
labels[fields.InputDataFields.groundtruth_classes] is a
[num_boxes, num_classes] float32 one-hot tensor of classes.
labels[fields.InputDataFields.groundtruth_area] is a [1, num_boxes]
float32 tensor containing object areas.
labels[fields.InputDataFields.groundtruth_is_crowd] is a [1, num_boxes]
bool tensor indicating if the boxes enclose a crowd.
labels[fields.InputDataFields.groundtruth_difficult] is a [1, num_boxes]
int32 tensor indicating if the boxes represent difficult instances.
-- Optional --
labels[fields.InputDataFields.groundtruth_instance_masks] is a
[1, num_boxes, H, W] float32 tensor containing only binary values,
which represent instance masks for objects.
Raises:
TypeError: if the `eval_config` or `eval_input_config` are not of the
correct type.
"""
del params
if not isinstance(eval_config, eval_pb2.EvalConfig):
raise TypeError('For eval mode, the `eval_config` must be a '
'train_pb2.EvalConfig.')
if not isinstance(eval_input_config, input_reader_pb2.InputReader):
raise TypeError('The `eval_input_config` must be a '
'input_reader_pb2.InputReader.')
if not isinstance(model_config, model_pb2.DetectionModel):
raise TypeError('The `model_config` must be a '
'model_pb2.DetectionModel.')
num_classes = config_util.get_number_of_classes(model_config)
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data, model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None,
retain_original_image=True)
dataset = dataset_builder.build(eval_input_config,
transform_input_data_fn=transform_data_fn)
input_dict = dataset_util.make_initializable_iterator(dataset).get_next()
hash_from_source_id = tf.string_to_hash_bucket_fast(
input_dict[fields.InputDataFields.source_id], HASH_BINS)
features = {
fields.InputDataFields.image:
input_dict[fields.InputDataFields.image],
fields.InputDataFields.original_image:
input_dict[fields.InputDataFields.original_image],
HASH_KEY: tf.cast(hash_from_source_id, tf.int32),
fields.InputDataFields.true_image_shape:
input_dict[fields.InputDataFields.true_image_shape]
}
labels = {
fields.InputDataFields.groundtruth_boxes:
input_dict[fields.InputDataFields.groundtruth_boxes],
fields.InputDataFields.groundtruth_classes:
input_dict[fields.InputDataFields.groundtruth_classes],
fields.InputDataFields.groundtruth_area:
input_dict[fields.InputDataFields.groundtruth_area],
fields.InputDataFields.groundtruth_is_crowd:
input_dict[fields.InputDataFields.groundtruth_is_crowd],
fields.InputDataFields.groundtruth_difficult:
tf.cast(input_dict[fields.InputDataFields.groundtruth_difficult],
tf.int32)
}
if fields.InputDataFields.groundtruth_instance_masks in input_dict:
labels[fields.InputDataFields.groundtruth_instance_masks] = input_dict[
fields.InputDataFields.groundtruth_instance_masks]
# Add a batch dimension to the tensors.
features = {
key: tf.expand_dims(features[key], axis=0)
for key, feature in features.items()
}
labels = {
key: tf.expand_dims(labels[key], axis=0)
for key, label in labels.items()
}
return features, labels
def _train_input_fn(params=None):
"""Returns `features` and `labels` tensor dictionaries for training.
Args:
params: Parameter dictionary passed from the estimator.
Returns:
features: Dictionary of feature tensors.
features[fields.InputDataFields.image] is a [batch_size, H, W, C]
float32 tensor with preprocessed images.
features[HASH_KEY] is a [batch_size] int32 tensor representing unique
identifiers for the images.
features[fields.InputDataFields.true_image_shape] is a [batch_size, 3]
int32 tensor representing the true image shapes, as preprocessed
images could be padded.
labels: Dictionary of groundtruth tensors.
labels[fields.InputDataFields.num_groundtruth_boxes] is a [batch_size]
int32 tensor indicating the number of groundtruth boxes.
labels[fields.InputDataFields.groundtruth_boxes] is a
[batch_size, num_boxes, 4] float32 tensor containing the corners of
the groundtruth boxes.
labels[fields.InputDataFields.groundtruth_classes] is a
[batch_size, num_boxes, num_classes] float32 one-hot tensor of
classes.
labels[fields.InputDataFields.groundtruth_weights] is a
[batch_size, num_boxes] float32 tensor containing groundtruth weights
for the boxes.
-- Optional --
labels[fields.InputDataFields.groundtruth_instance_masks] is a
[batch_size, num_boxes, H, W] float32 tensor containing only binary
values, which represent instance masks for objects.
labels[fields.InputDataFields.groundtruth_keypoints] is a
[batch_size, num_boxes, num_keypoints, 2] float32 tensor containing
keypoints for each box.
Raises:
TypeError: if the `train_config` or `train_input_config` are not of the
correct type.
"""
if not isinstance(train_config, train_pb2.TrainConfig):
raise TypeError('For training mode, the `train_config` must be a '
'train_pb2.TrainConfig.')
if not isinstance(train_input_config, input_reader_pb2.InputReader):
raise TypeError('The `train_input_config` must be a '
'input_reader_pb2.InputReader.')
if not isinstance(model_config, model_pb2.DetectionModel):
raise TypeError('The `model_config` must be a '
'model_pb2.DetectionModel.')
data_augmentation_options = [
preprocessor_builder.build(step)
for step in train_config.data_augmentation_options
]
data_augmentation_fn = functools.partial(
augment_input_data, data_augmentation_options=data_augmentation_options)
model = model_builder.build(model_config, is_training=True)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data, model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=config_util.get_number_of_classes(model_config),
data_augmentation_fn=data_augmentation_fn)
dataset = dataset_builder.build(
train_input_config,
transform_input_data_fn=transform_data_fn,
batch_size=params['batch_size'] if params else train_config.batch_size,
max_num_boxes=train_config.max_number_of_boxes,
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
tensor_dict = dataset_util.make_initializable_iterator(dataset).get_next()
hash_from_source_id = tf.string_to_hash_bucket_fast(
tensor_dict[fields.InputDataFields.source_id], HASH_BINS)
features = {
fields.InputDataFields.image: tensor_dict[fields.InputDataFields.image],
HASH_KEY: tf.cast(hash_from_source_id, tf.int32),
fields.InputDataFields.true_image_shape: tensor_dict[
fields.InputDataFields.true_image_shape]
}
labels = {
fields.InputDataFields.num_groundtruth_boxes: tensor_dict[
fields.InputDataFields.num_groundtruth_boxes],
fields.InputDataFields.groundtruth_boxes: tensor_dict[
fields.InputDataFields.groundtruth_boxes],
fields.InputDataFields.groundtruth_classes: tensor_dict[
fields.InputDataFields.groundtruth_classes],
fields.InputDataFields.groundtruth_weights: tensor_dict[
fields.InputDataFields.groundtruth_weights]
}
if fields.InputDataFields.groundtruth_keypoints in tensor_dict:
labels[fields.InputDataFields.groundtruth_keypoints] = tensor_dict[
fields.InputDataFields.groundtruth_keypoints]
if fields.InputDataFields.groundtruth_instance_masks in tensor_dict:
labels[fields.InputDataFields.groundtruth_instance_masks] = tensor_dict[
fields.InputDataFields.groundtruth_instance_masks]
return features, labels
def _eval_input_fn(params=None):
"""Returns `features` and `labels` tensor dictionaries for evaluation.
Args:
params: Parameter dictionary passed from the estimator.
Returns:
features: Dictionary of feature tensors.
features[fields.InputDataFields.image] is a [1, H, W, C] float32 tensor
with preprocessed images.
features[HASH_KEY] is a [1] int32 tensor representing unique
identifiers for the images.
features[fields.InputDataFields.true_image_shape] is a [1, 3]
int32 tensor representing the true image shapes, as preprocessed
images could be padded.
features[fields.InputDataFields.original_image] is a [1, H', W', C]
float32 tensor with the original image.
labels: Dictionary of groundtruth tensors.
labels[fields.InputDataFields.groundtruth_boxes] is a [1, num_boxes, 4]
float32 tensor containing the corners of the groundtruth boxes.
labels[fields.InputDataFields.groundtruth_classes] is a
[num_boxes, num_classes] float32 one-hot tensor of classes.
labels[fields.InputDataFields.groundtruth_area] is a [1, num_boxes]
float32 tensor containing object areas.
labels[fields.InputDataFields.groundtruth_is_crowd] is a [1, num_boxes]
bool tensor indicating if the boxes enclose a crowd.
labels[fields.InputDataFields.groundtruth_difficult] is a [1, num_boxes]
int32 tensor indicating if the boxes represent difficult instances.
-- Optional --
labels[fields.InputDataFields.groundtruth_instance_masks] is a
[1, num_boxes, H, W] float32 tensor containing only binary values,
which represent instance masks for objects.
Raises:
TypeError: if the `eval_config`, `eval_input_config` or `model_config`
are not of the correct type.
"""
params = params or {}
if not isinstance(eval_config, eval_pb2.EvalConfig):
raise TypeError('For eval mode, the `eval_config` must be a '
'train_pb2.EvalConfig.')
if not isinstance(eval_input_config, input_reader_pb2.InputReader):
raise TypeError('The `eval_input_config` must be a '
'input_reader_pb2.InputReader.')
if not isinstance(model_config, model_pb2.DetectionModel):
raise TypeError('The `model_config` must be a '
'model_pb2.DetectionModel.')
num_classes = config_util.get_number_of_classes(model_config)
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_util.get_image_resizer_config(model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
transform_data_fn = functools.partial(
transform_input_data, model_preprocess_fn=model.preprocess,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=None,
retain_original_image=eval_config.retain_original_images)
dataset = INPUT_BUILDER_UTIL_MAP['dataset_build'](
eval_input_config,
transform_input_data_fn=transform_data_fn,
batch_size=params.get('batch_size', 1),
num_classes=config_util.get_number_of_classes(model_config),
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config))
input_dict = dataset_util.make_initializable_iterator(dataset).get_next()
return (_get_features_dict(input_dict), _get_labels_dict(input_dict))
def train_input(train_config,
train_input_config,
model_config,
model=None,
params=None):
"""Returns `features` and `labels` tensor dictionaries for training.
Args:
train_config: A train_pb2.TrainConfig.
train_input_config: An input_reader_pb2.InputReader.
model_config: A model_pb2.DetectionModel.
model: A pre-constructed Detection Model.
If None, one will be created from the config.
params: Parameter dictionary passed from the estimator.
Returns:
A tf.data.Dataset that holds (features, labels) tuple.
features: Dictionary of feature tensors.
features[fields.InputDataFields.image] is a [batch_size, H, W, C]
float32 tensor with preprocessed images.
features[HASH_KEY] is a [batch_size] int32 tensor representing unique
identifiers for the images.
features[fields.InputDataFields.true_image_shape] is a [batch_size, 3]
int32 tensor representing the true image shapes, as preprocessed
images could be padded.
features[fields.InputDataFields.original_image] (optional) is a
[batch_size, H, W, C] float32 tensor with original images.
labels: Dictionary of groundtruth tensors.
labels[fields.InputDataFields.num_groundtruth_boxes] is a [batch_size]
int32 tensor indicating the number of groundtruth boxes.
labels[fields.InputDataFields.groundtruth_boxes] is a
[batch_size, num_boxes, 4] float32 tensor containing the corners of
the groundtruth boxes.
labels[fields.InputDataFields.groundtruth_classes] is a
[batch_size, num_boxes, num_classes] float32 one-hot tensor of
classes.
labels[fields.InputDataFields.groundtruth_weights] is a
[batch_size, num_boxes] float32 tensor containing groundtruth weights
for the boxes.
-- Optional --
labels[fields.InputDataFields.groundtruth_instance_masks] is a
[batch_size, num_boxes, H, W] float32 tensor containing only binary
values, which represent instance masks for objects.
labels[fields.InputDataFields.groundtruth_keypoints] is a
[batch_size, num_boxes, num_keypoints, 2] float32 tensor containing
keypoints for each box.
labels[fields.InputDataFields.groundtruth_weights] is a
[batch_size, num_boxes, num_keypoints] float32 tensor containing
groundtruth weights for the keypoints.
labels[fields.InputDataFields.groundtruth_visibilities] is a
[batch_size, num_boxes, num_keypoints] bool tensor containing
groundtruth visibilities for each keypoint.
Raises:
TypeError: if the `train_config`, `train_input_config` or `model_config`
are not of the correct type.
"""
if not isinstance(train_config, train_pb2.TrainConfig):
raise TypeError('For training mode, the `train_config` must be a '
'train_pb2.TrainConfig.')
if not isinstance(train_input_config, input_reader_pb2.InputReader):
raise TypeError('The `train_input_config` must be a '
'input_reader_pb2.InputReader.')
if not isinstance(model_config, model_pb2.DetectionModel):
raise TypeError('The `model_config` must be a '
'model_pb2.DetectionModel.')
if model is None:
model_preprocess_fn = INPUT_BUILDER_UTIL_MAP['model_build'](
model_config, is_training=True).preprocess
else:
model_preprocess_fn = model.preprocess
num_classes = config_util.get_number_of_classes(model_config)
def transform_and_pad_input_data_fn(tensor_dict):
"""Combines transform and pad operation."""
data_augmentation_options = [
preprocessor_builder.build(step)
for step in train_config.data_augmentation_options
]
data_augmentation_fn = functools.partial(
augment_input_data,
data_augmentation_options=data_augmentation_options)
image_resizer_config = config_util.get_image_resizer_config(
model_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
keypoint_type_weight = train_input_config.keypoint_type_weight or None
transform_data_fn = functools.partial(
transform_input_data,
model_preprocess_fn=model_preprocess_fn,
image_resizer_fn=image_resizer_fn,
num_classes=num_classes,
data_augmentation_fn=data_augmentation_fn,
merge_multiple_boxes=train_config.merge_multiple_label_boxes,
retain_original_image=train_config.retain_original_images,
use_multiclass_scores=train_config.use_multiclass_scores,
use_bfloat16=train_config.use_bfloat16,
keypoint_type_weight=keypoint_type_weight)
tensor_dict = pad_input_data_to_static_shapes(
tensor_dict=transform_data_fn(tensor_dict),
max_num_boxes=train_input_config.max_number_of_boxes,
num_classes=num_classes,
spatial_image_shape=config_util.get_spatial_image_size(
image_resizer_config),
max_num_context_features=config_util.get_max_num_context_features(
model_config),
context_feature_length=config_util.get_context_feature_length(
model_config))
return (_get_features_dict(tensor_dict), _get_labels_dict(tensor_dict))
dataset = INPUT_BUILDER_UTIL_MAP['dataset_build'](
train_input_config,
transform_input_data_fn=transform_and_pad_input_data_fn,
batch_size=params['batch_size'] if params else train_config.batch_size)
return dataset
