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_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 _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 _build_ssd_model(ssd_config, is_training, add_summaries):
"""Builds an SSD detection model based on the model config.
Args:
ssd_config: A ssd.proto object containing the config for the desired
SSDMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
SSDMetaArch based on the config.
Raises:
ValueError: If ssd_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = ssd_config.num_classes
# Feature extractor
feature_extractor = _build_ssd_feature_extractor(
ssd_config.feature_extractor, is_training)
box_coder = box_coder_builder.build(ssd_config.box_coder)
matcher = matcher_builder.build(ssd_config.matcher)
region_similarity_calculator = sim_calc.build(
ssd_config.similarity_calculator)
encode_background_as_zeros = ssd_config.encode_background_as_zeros
ssd_box_predictor = box_predictor_builder.build(hyperparams_builder.build,
ssd_config.box_predictor,
is_training, num_classes)
anchor_generator = anchor_generator_builder.build(
ssd_config.anchor_generator)
image_resizer_fn = image_resizer_builder.build(ssd_config.image_resizer)
non_max_suppression_fn, score_conversion_fn = post_processing_builder.build(
ssd_config.post_processing)
(classification_loss, localization_loss, classification_weight,
localization_weight,
hard_example_miner) = losses_builder.build(ssd_config.loss)
normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches
return ssd_meta_arch.SSDMetaArch(is_training,
anchor_generator,
ssd_box_predictor,
box_coder,
feature_extractor,
matcher,
region_similarity_calculator,
encode_background_as_zeros,
image_resizer_fn,
non_max_suppression_fn,
score_conversion_fn,
classification_loss,
localization_loss,
classification_weight,
localization_weight,
normalize_loss_by_num_matches,
hard_example_miner,
add_summaries=add_summaries)
def _resized_image_given_text_proto(self, image, text_proto):
image_resizer_config = image_resizer_pb2.ImageResizer()
text_format.Merge(text_proto, image_resizer_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
image_placeholder = tf.placeholder(tf.uint8, [1, None, None, 3])
resized_image, _ = image_resizer_fn(image_placeholder)
with self.test_session() as sess:
return sess.run(resized_image,
feed_dict={image_placeholder: image})
def _shape_of_resized_random_image_given_text_proto(
self, input_shape, text_proto):
image_resizer_config = image_resizer_pb2.ImageResizer()
text_format.Merge(text_proto, image_resizer_config)
image_resizer_fn = image_resizer_builder.build(image_resizer_config)
images = tf.to_float(tf.random_uniform(
input_shape, minval=0, maxval=255, dtype=tf.int32))
resized_images = image_resizer_fn(images)
with self.test_session() as sess:
return sess.run(resized_images).shape
def transform_and_pad_input_data_fn(tensor_dict):
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_utils.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)
tensor_dict = transform_data_fn(tensor_dict)
return (_get_features_dict(tensor_dict), _get_label_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 _predict_input_fn(params=None):
del params
example = tf.placeholder(dtype=tf.string, shape=[], name='tf_example')
model = model_builder.build(model_config, is_training=False)
image_resizer_config = config_utils.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)
decoder = tf_example_decoder.TfExampleDecoder()
input_dict = transform_fn(decoder.decode(example))
images = tf.to_float(input_dict[fields.InputDataFields.image])
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 _build_faster_rcnn_model(frcnn_config, is_training):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor, is_training)
first_stage_only = frcnn_config.first_stage_only
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_arg_scope = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
first_stage_positive_balance_fraction = (
frcnn_config.first_stage_positive_balance_fraction)
first_stage_nms_score_threshold = frcnn_config.first_stage_nms_score_threshold
first_stage_nms_iou_threshold = frcnn_config.first_stage_nms_iou_threshold
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_balance_fraction = frcnn_config.second_stage_balance_fraction
(second_stage_non_max_suppression_fn, second_stage_score_conversion_fn
) = post_processing_builder.build(frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'first_stage_only': first_stage_only,
'first_stage_anchor_generator': first_stage_anchor_generator,
'first_stage_atrous_rate': first_stage_atrous_rate,
'first_stage_box_predictor_arg_scope':
first_stage_box_predictor_arg_scope,
'first_stage_box_predictor_kernel_size':
first_stage_box_predictor_kernel_size,
'first_stage_box_predictor_depth': first_stage_box_predictor_depth,
'first_stage_minibatch_size': first_stage_minibatch_size,
'first_stage_positive_balance_fraction':
first_stage_positive_balance_fraction,
'first_stage_nms_score_threshold': first_stage_nms_score_threshold,
'first_stage_nms_iou_threshold': first_stage_nms_iou_threshold,
'first_stage_max_proposals': first_stage_max_proposals,
'first_stage_localization_loss_weight': first_stage_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_loss_weight,
'second_stage_batch_size': second_stage_batch_size,
'second_stage_balance_fraction': second_stage_balance_fraction,
'second_stage_non_max_suppression_fn':
second_stage_non_max_suppression_fn,
'second_stage_score_conversion_fn': second_stage_score_conversion_fn,
'second_stage_localization_loss_weight':
second_stage_localization_loss_weight,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner': hard_example_miner}
if isinstance(second_stage_box_predictor, box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
**common_kwargs)
def _build_faster_rcnn_model(frcnn_config, is_training, add_summaries):
"""Builds a Faster R-CNN or R-FCN detection model based on the model config.
Builds R-FCN model if the second_stage_box_predictor in the config is of type
`rfcn_box_predictor` else builds a Faster R-CNN model.
Args:
frcnn_config: A faster_rcnn.proto object containing the config for the
desired FasterRCNNMetaArch or RFCNMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
FasterRCNNMetaArch based on the config.
Raises:
ValueError: If frcnn_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = frcnn_config.num_classes
image_resizer_fn = image_resizer_builder.build(frcnn_config.image_resizer)
feature_extractor = _build_faster_rcnn_feature_extractor(
frcnn_config.feature_extractor,
is_training,
inplace_batchnorm_update=frcnn_config.inplace_batchnorm_update)
number_of_stages = frcnn_config.number_of_stages
first_stage_anchor_generator = anchor_generator_builder.build(
frcnn_config.first_stage_anchor_generator)
first_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'proposal',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
first_stage_atrous_rate = frcnn_config.first_stage_atrous_rate
first_stage_box_predictor_arg_scope_fn = hyperparams_builder.build(
frcnn_config.first_stage_box_predictor_conv_hyperparams, is_training)
first_stage_box_predictor_kernel_size = (
frcnn_config.first_stage_box_predictor_kernel_size)
first_stage_box_predictor_depth = frcnn_config.first_stage_box_predictor_depth
first_stage_minibatch_size = frcnn_config.first_stage_minibatch_size
use_static_shapes = frcnn_config.use_static_shapes and (
frcnn_config.use_static_shapes_for_eval or is_training)
first_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.first_stage_positive_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler
and use_static_shapes))
first_stage_max_proposals = frcnn_config.first_stage_max_proposals
if (frcnn_config.first_stage_nms_iou_threshold < 0
or frcnn_config.first_stage_nms_iou_threshold > 1.0):
raise ValueError('iou_threshold not in [0, 1.0].')
if (is_training and
frcnn_config.second_stage_batch_size > first_stage_max_proposals):
raise ValueError('second_stage_batch_size should be no greater than '
'first_stage_max_proposals.')
first_stage_non_max_suppression_fn = functools.partial(
post_processing.batch_multiclass_non_max_suppression,
score_thresh=frcnn_config.first_stage_nms_score_threshold,
iou_thresh=frcnn_config.first_stage_nms_iou_threshold,
max_size_per_class=frcnn_config.first_stage_max_proposals,
max_total_size=frcnn_config.first_stage_max_proposals,
use_static_shapes=use_static_shapes)
first_stage_loc_loss_weight = (
frcnn_config.first_stage_localization_loss_weight)
first_stage_obj_loss_weight = frcnn_config.first_stage_objectness_loss_weight
initial_crop_size = frcnn_config.initial_crop_size
maxpool_kernel_size = frcnn_config.maxpool_kernel_size
maxpool_stride = frcnn_config.maxpool_stride
second_stage_target_assigner = target_assigner.create_target_assigner(
'FasterRCNN',
'detection',
use_matmul_gather=frcnn_config.use_matmul_gather_in_matcher)
second_stage_box_predictor = box_predictor_builder.build(
hyperparams_builder.build,
frcnn_config.second_stage_box_predictor,
is_training=is_training,
num_classes=num_classes)
second_stage_batch_size = frcnn_config.second_stage_batch_size
second_stage_sampler = sampler.BalancedPositiveNegativeSampler(
positive_fraction=frcnn_config.second_stage_balance_fraction,
is_static=(frcnn_config.use_static_balanced_label_sampler
and use_static_shapes))
(second_stage_non_max_suppression_fn,
second_stage_score_conversion_fn) = post_processing_builder.build(
frcnn_config.second_stage_post_processing)
second_stage_localization_loss_weight = (
frcnn_config.second_stage_localization_loss_weight)
second_stage_classification_loss = (
losses_builder.build_faster_rcnn_classification_loss(
frcnn_config.second_stage_classification_loss))
second_stage_classification_loss_weight = (
frcnn_config.second_stage_classification_loss_weight)
second_stage_mask_prediction_loss_weight = (
frcnn_config.second_stage_mask_prediction_loss_weight)
hard_example_miner = None
if frcnn_config.HasField('hard_example_miner'):
hard_example_miner = losses_builder.build_hard_example_miner(
frcnn_config.hard_example_miner,
second_stage_classification_loss_weight,
second_stage_localization_loss_weight)
crop_and_resize_fn = (ops.matmul_crop_and_resize
if frcnn_config.use_matmul_crop_and_resize else
ops.native_crop_and_resize)
clip_anchors_to_image = (frcnn_config.clip_anchors_to_image)
common_kwargs = {
'is_training': is_training,
'num_classes': num_classes,
'image_resizer_fn': image_resizer_fn,
'feature_extractor': feature_extractor,
'number_of_stages': number_of_stages,
'first_stage_anchor_generator': first_stage_anchor_generator,
'first_stage_target_assigner': first_stage_target_assigner,
'first_stage_atrous_rate': first_stage_atrous_rate,
'first_stage_box_predictor_arg_scope_fn':
first_stage_box_predictor_arg_scope_fn,
'first_stage_box_predictor_kernel_size':
first_stage_box_predictor_kernel_size,
'first_stage_box_predictor_depth': first_stage_box_predictor_depth,
'first_stage_minibatch_size': first_stage_minibatch_size,
'first_stage_sampler': first_stage_sampler,
'first_stage_non_max_suppression_fn':
first_stage_non_max_suppression_fn,
'first_stage_max_proposals': first_stage_max_proposals,
'first_stage_localization_loss_weight': first_stage_loc_loss_weight,
'first_stage_objectness_loss_weight': first_stage_obj_loss_weight,
'second_stage_target_assigner': second_stage_target_assigner,
'second_stage_batch_size': second_stage_batch_size,
'second_stage_sampler': second_stage_sampler,
'second_stage_non_max_suppression_fn':
second_stage_non_max_suppression_fn,
'second_stage_score_conversion_fn': second_stage_score_conversion_fn,
'second_stage_localization_loss_weight':
second_stage_localization_loss_weight,
'second_stage_classification_loss': second_stage_classification_loss,
'second_stage_classification_loss_weight':
second_stage_classification_loss_weight,
'hard_example_miner': hard_example_miner,
'add_summaries': add_summaries,
'crop_and_resize_fn': crop_and_resize_fn,
'clip_anchors_to_image': clip_anchors_to_image,
'use_static_shapes': use_static_shapes,
'resize_masks': frcnn_config.resize_masks
}
if isinstance(second_stage_box_predictor,
rfcn_box_predictor.RfcnBoxPredictor):
return rfcn_meta_arch.RFCNMetaArch(
second_stage_rfcn_box_predictor=second_stage_box_predictor,
**common_kwargs)
else:
return faster_rcnn_meta_arch.FasterRCNNMetaArch(
initial_crop_size=initial_crop_size,
maxpool_kernel_size=maxpool_kernel_size,
maxpool_stride=maxpool_stride,
second_stage_mask_rcnn_box_predictor=second_stage_box_predictor,
second_stage_mask_prediction_loss_weight=(
second_stage_mask_prediction_loss_weight),
**common_kwargs)
def _build_ssd_model(ssd_config, is_training, add_summaries):
"""Builds an SSD detection model based on the model config.
Args:
ssd_config: A ssd.proto object containing the config for the desired
SSDMetaArch.
is_training: True if this model is being built for training purposes.
add_summaries: Whether to add tf summaries in the model.
Returns:
SSDMetaArch based on the config.
Raises:
ValueError: If ssd_config.type is not recognized (i.e. not registered in
model_class_map).
"""
num_classes = ssd_config.num_classes
# Feature extractor
feature_extractor = _build_ssd_feature_extractor(
feature_extractor_config=ssd_config.feature_extractor,
freeze_batchnorm=ssd_config.freeze_batchnorm,
is_training=is_training)
box_coder = box_coder_builder.build(ssd_config.box_coder)
matcher = matcher_builder.build(ssd_config.matcher)
region_similarity_calculator = sim_calc.build(
ssd_config.similarity_calculator)
encode_background_as_zeros = ssd_config.encode_background_as_zeros
negative_class_weight = ssd_config.negative_class_weight
anchor_generator = anchor_generator_builder.build(
ssd_config.anchor_generator)
if feature_extractor.is_keras_model:
ssd_box_predictor = box_predictor_builder.build_keras(
conv_hyperparams_fn=hyperparams_builder.KerasLayerHyperparams,
freeze_batchnorm=ssd_config.freeze_batchnorm,
inplace_batchnorm_update=False,
num_predictions_per_location_list=anchor_generator.
num_anchors_per_location(),
box_predictor_config=ssd_config.box_predictor,
is_training=is_training,
num_classes=num_classes,
add_background_class=ssd_config.add_background_class)
else:
ssd_box_predictor = box_predictor_builder.build(
hyperparams_builder.build, ssd_config.box_predictor, is_training,
num_classes, ssd_config.add_background_class)
image_resizer_fn = image_resizer_builder.build(ssd_config.image_resizer)
non_max_suppression_fn, score_conversion_fn = post_processing_builder.build(
ssd_config.post_processing)
(classification_loss, localization_loss, classification_weight,
localization_weight, hard_example_miner, random_example_sampler,
expected_loss_weights_fn) = losses_builder.build(ssd_config.loss)
normalize_loss_by_num_matches = ssd_config.normalize_loss_by_num_matches
normalize_loc_loss_by_codesize = ssd_config.normalize_loc_loss_by_codesize
equalization_loss_config = ops.EqualizationLossConfig(
weight=ssd_config.loss.equalization_loss.weight,
exclude_prefixes=ssd_config.loss.equalization_loss.exclude_prefixes)
target_assigner_instance = target_assigner.TargetAssigner(
region_similarity_calculator,
matcher,
box_coder,
negative_class_weight=negative_class_weight)
ssd_meta_arch_fn = ssd_meta_arch.SSDMetaArch
kwargs = {}
return ssd_meta_arch_fn(
is_training=is_training,
anchor_generator=anchor_generator,
box_predictor=ssd_box_predictor,
box_coder=box_coder,
feature_extractor=feature_extractor,
encode_background_as_zeros=encode_background_as_zeros,
image_resizer_fn=image_resizer_fn,
non_max_suppression_fn=non_max_suppression_fn,
score_conversion_fn=score_conversion_fn,
classification_loss=classification_loss,
localization_loss=localization_loss,
classification_loss_weight=classification_weight,
localization_loss_weight=localization_weight,
normalize_loss_by_num_matches=normalize_loss_by_num_matches,
hard_example_miner=hard_example_miner,
target_assigner_instance=target_assigner_instance,
add_summaries=add_summaries,
normalize_loc_loss_by_codesize=normalize_loc_loss_by_codesize,
freeze_batchnorm=ssd_config.freeze_batchnorm,
inplace_batchnorm_update=ssd_config.inplace_batchnorm_update,
add_background_class=ssd_config.add_background_class,
explicit_background_class=ssd_config.explicit_background_class,
random_example_sampler=random_example_sampler,
expected_loss_weights_fn=expected_loss_weights_fn,
use_confidences_as_targets=ssd_config.use_confidences_as_targets,
implicit_example_weight=ssd_config.implicit_example_weight,
equalization_loss_config=equalization_loss_config,
**kwargs)
def test_raises_error_on_invalid_input(self):
invalid_input = 'invalid_input'
with self.assertRaises(ValueError):
image_resizer_builder.build(invalid_input)
def _build_cnn_model(cnn_config, is_training, add_summaries):
image_resizer_fn = image_resizer_builder.build(cnn_config.image_resizer)
cnn_meta_arch_fn = cnn_meta_arch.CnnMetaArch
return cnn_meta_arch_fn(is_training=is_training,
image_resizer_fn=image_resizer_fn,
config=cnn_config)
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
