Python object_detection.utils.config_util.get_image_resizer_config() Examples
The following are 26
code examples of object_detection.utils.config_util.get_image_resizer_config().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
object_detection.utils.config_util
, or try the search function
.
.
Example #1
| Source File: config_util_test.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 5 votes |
|
def testGetImageResizerConfig(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #2
| Source File: config_util_test.py From multilabel-image-classification-tensorflow with MIT License | 5 votes |
|
def testGetImageResizerConfig(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #3
| Source File: config_util_test.py From models with Apache License 2.0 | 5 votes |
|
def testGetImageResizerConfig(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #4
| Source File: config_util_test.py From g-tensorflow-models with Apache License 2.0 | 5 votes |
|
def testGetImageResizerConfig(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #5
| Source File: config_util_test.py From MAX-Object-Detector with Apache License 2.0 | 5 votes |
|
def testGetImageResizerConfig(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #6
| Source File: config_util_test.py From AniSeg with Apache License 2.0 | 5 votes |
|
def test_get_image_resizer_config(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #7
| Source File: config_util_test.py From Elphas with Apache License 2.0 | 5 votes |
|
def test_get_image_resizer_config(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #8
| Source File: config_util_test.py From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 | 5 votes |
|
def testGetImageResizerConfig(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #9
| Source File: config_util_test.py From ros_tensorflow with Apache License 2.0 | 5 votes |
|
def test_get_image_resizer_config(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #10
| Source File: config_util_test.py From Person-Detection-and-Tracking with MIT License | 5 votes |
|
def test_get_image_resizer_config(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #11
| Source File: config_util_test.py From vehicle_counting_tensorflow with MIT License | 5 votes |
|
def testGetImageResizerConfig(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #12
| Source File: config_util_test.py From ros_people_object_detection_tensorflow with Apache License 2.0 | 5 votes |
|
def test_get_image_resizer_config(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #13
| Source File: config_util_test.py From Gun-Detector with Apache License 2.0 | 5 votes |
|
def test_get_image_resizer_config(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #14
| Source File: config_util_test.py From Traffic-Rule-Violation-Detection-System with MIT License | 5 votes |
|
def test_get_image_resizer_config(self):
"""Tests that number of classes can be retrieved."""
model_config = model_pb2.DetectionModel()
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.height = 100
model_config.faster_rcnn.image_resizer.fixed_shape_resizer.width = 300
image_resizer_config = config_util.get_image_resizer_config(model_config)
self.assertEqual(image_resizer_config.fixed_shape_resizer.height, 100)
self.assertEqual(image_resizer_config.fixed_shape_resizer.width, 300)
Example #15
| Source File: inputs.py From vehicle_counting_tensorflow with MIT License | 4 votes |
|
def create_predict_input_fn(model_config, predict_input_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
predict_input_config: An input_reader_pb2.InputReader.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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 = 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,
num_additional_channels=predict_input_config.num_additional_channels)
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})
return _predict_input_fn
Example #16
| Source File: inputs.py From Elphas with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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})
return _predict_input_fn
Example #17
| Source File: inputs.py From Traffic-Rule-Violation-Detection-System with MIT License | 4 votes |
|
def create_predict_input_fn(model_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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})
return _predict_input_fn
Example #18
| Source File: inputs.py From BMW-TensorFlow-Training-GUI with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config, predict_input_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
predict_input_config: An input_reader_pb2.InputReader.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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 = 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,
num_additional_channels=predict_input_config.num_additional_channels)
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})
return _predict_input_fn
Example #19
| Source File: inputs.py From MAX-Object-Detector with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config, predict_input_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
predict_input_config: An input_reader_pb2.InputReader.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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 = 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,
num_additional_channels=predict_input_config.num_additional_channels)
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})
return _predict_input_fn
Example #20
| Source File: inputs.py From Person-Detection-and-Tracking with MIT License | 4 votes |
|
def create_predict_input_fn(model_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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)
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})
return _predict_input_fn
Example #21
| Source File: inputs.py From g-tensorflow-models with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config, predict_input_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
predict_input_config: An input_reader_pb2.InputReader.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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 = 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,
num_additional_channels=predict_input_config.num_additional_channels)
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})
return _predict_input_fn
Example #22
| Source File: inputs.py From Gun-Detector with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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)
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})
return _predict_input_fn
Example #23
| Source File: inputs.py From models with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config, predict_input_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
predict_input_config: An input_reader_pb2.InputReader.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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_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})
return _predict_input_fn
Example #24
| Source File: inputs.py From ros_people_object_detection_tensorflow with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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)
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})
return _predict_input_fn
Example #25
| Source File: inputs.py From multilabel-image-classification-tensorflow with MIT License | 4 votes |
|
def create_predict_input_fn(model_config, predict_input_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
predict_input_config: An input_reader_pb2.InputReader.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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 = 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,
num_additional_channels=predict_input_config.num_additional_channels)
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})
return _predict_input_fn
Example #26
| Source File: inputs.py From ros_tensorflow with Apache License 2.0 | 4 votes |
|
def create_predict_input_fn(model_config):
"""Creates a predict `input` function for `Estimator`.
Args:
model_config: A model_pb2.DetectionModel.
Returns:
`input_fn` for `Estimator` in PREDICT mode.
"""
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)
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})
return _predict_input_fn
