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 test_get_spatial_image_size_from_aspect_preserving_resizer_dynamic(
self):
image_resizer_config = image_resizer_pb2.ImageResizer()
image_resizer_config.keep_aspect_ratio_resizer.min_dimension = 100
image_resizer_config.keep_aspect_ratio_resizer.max_dimension = 600
image_shape = config_util.get_spatial_image_size(image_resizer_config)
self.assertAllEqual(image_shape, [-1, -1])
def test_get_spatial_image_size_from_aspect_preserving_resizer_config(self): image_resizer_config = image_resizer_pb2.ImageResizer() image_resizer_config.keep_aspect_ratio_resizer.min_dimension = 100 image_resizer_config.keep_aspect_ratio_resizer.max_dimension = 600 image_resizer_config.keep_aspect_ratio_resizer.pad_to_max_dimension = True image_shape = config_util.get_spatial_image_size(image_resizer_config) self.assertAllEqual(image_shape, [600, 600])
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 testGetSpatialImageSizeFromAspectPreservingResizerConfig(self):
image_resizer_config = image_resizer_pb2.ImageResizer()
image_resizer_config.keep_aspect_ratio_resizer.min_dimension = 100
image_resizer_config.keep_aspect_ratio_resizer.max_dimension = 600
image_resizer_config.keep_aspect_ratio_resizer.pad_to_max_dimension = True
image_shape = config_util.get_spatial_image_size(image_resizer_config)
self.assertAllEqual(image_shape, [600, 600])
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."""
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 test_get_spatial_image_size_from_fixed_shape_resizer_config(self):
image_resizer_config = image_resizer_pb2.ImageResizer()
image_resizer_config.fixed_shape_resizer.height = 100
image_resizer_config.fixed_shape_resizer.width = 200
image_shape = config_util.get_spatial_image_size(image_resizer_config)
self.assertAllEqual(image_shape, [100, 200])
def test_get_spatial_image_size_from_fixed_shape_resizer_config(self): image_resizer_config = image_resizer_pb2.ImageResizer() image_resizer_config.fixed_shape_resizer.height = 100 image_resizer_config.fixed_shape_resizer.width = 200 image_shape = config_util.get_spatial_image_size(image_resizer_config) self.assertAllEqual(image_shape, [100, 200])
def testGetSpatialImageSizeFromConditionalShapeResizer(self):
image_resizer_config = image_resizer_pb2.ImageResizer()
image_resizer_config.conditional_shape_resizer.size_threshold = 100
image_shape = config_util.get_spatial_image_size(image_resizer_config)
self.assertAllEqual(image_shape, [-1, -1])
def testGetSpatialImageSizeFromAspectPreservingResizerDynamic(self): image_resizer_config = image_resizer_pb2.ImageResizer() image_resizer_config.keep_aspect_ratio_resizer.min_dimension = 100 image_resizer_config.keep_aspect_ratio_resizer.max_dimension = 600 image_shape = config_util.get_spatial_image_size(image_resizer_config) self.assertAllEqual(image_shape, [-1, -1])
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 _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))
