Python preprocessing.cifarnet_preprocessing() Examples
The following are 30
code examples of preprocessing.cifarnet_preprocessing().
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
preprocessing
, or try the search function
.
.
Example #1
| Source File: preprocessing_factory.py From MAX-Object-Detector with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'mobilenet_v2': inception_preprocessing,
'mobilenet_v2_035': inception_preprocessing,
'mobilenet_v2_140': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_mobile': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #2
| Source File: preprocessing_factory.py From TwinGAN with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
'danbooru': danbooru_preprocessing
}
if name is None or name == 'fully_connected':
tf.logging.info('No preprocessing.')
return None
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #3
| Source File: preprocessing_factory.py From Action_Recognition_Zoo with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #4
| Source File: preprocessing_factory.py From ECO-pytorch with BSD 2-Clause "Simplified" License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #5
| Source File: preprocessing_factory.py From Machine-Learning-with-TensorFlow-1.x with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #6
| Source File: preprocessing_factory.py From hands-detection with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #7
| Source File: preprocessing_factory.py From object_detection_kitti with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #8
| Source File: preprocessing_factory.py From MBMD with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #9
| Source File: preprocessing_factory.py From Optical-Flow-Guided-Feature with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
'off': off_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #10
| Source File: preprocessing_factory.py From object_detection_with_tensorflow with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #11
| Source File: preprocessing_factory.py From SENet-tensorflow-slim with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #12
| Source File: preprocessing_factory.py From style_swap_tensorflow with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #13
| Source File: preprocessing_factory.py From nasnet-tensorflow with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #14
| Source File: preprocessing_factory.py From HumanRecognition with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #15
| Source File: preprocessing_factory.py From g-tensorflow-models with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'mobilenet_v2': inception_preprocessing,
'mobilenet_v2_035': inception_preprocessing,
'mobilenet_v2_140': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_mobile': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #16
| Source File: preprocessing_factory.py From g-tensorflow-models with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #17
| Source File: preprocessing_factory.py From models with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #18
| Source File: preprocessing_factory.py From motion-rcnn with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #19
| Source File: preprocessing_factory.py From mtl-ssl with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #20
| Source File: preprocessing_factory.py From multilabel-image-classification-tensorflow with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'mobilenet_v2': inception_preprocessing,
'mobilenet_v2_035': inception_preprocessing,
'mobilenet_v2_140': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_mobile': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #21
| Source File: preprocessing_factory.py From multilabel-image-classification-tensorflow with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #22
| Source File: preprocessing_factory.py From Gun-Detector with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #23
| Source File: preprocessing_factory.py From STORK with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #24
| Source File: preprocessing_factory.py From ctw-baseline with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #25
| Source File: preprocessing_factory.py From tf-pose with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #26
| Source File: preprocessing_factory.py From edafa with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'mobilenet_v2': inception_preprocessing,
'mobilenet_v2_035': inception_preprocessing,
'mobilenet_v2_140': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'pnasnet_mobile': inception_preprocessing,
'pnasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #27
| Source File: preprocessing_factory.py From cv-tricks.com with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #28
| Source File: preprocessing_factory.py From garbage-object-detection-tensorflow with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #29
| Source File: preprocessing_factory.py From yolo_v2 with Apache License 2.0 | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'nasnet_mobile': inception_preprocessing,
'nasnet_large': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
Example #30
| Source File: preprocessing_factory.py From Hands-On-Machine-Learning-with-OpenCV-4 with MIT License | 4 votes |
|
def get_preprocessing(name, is_training=False):
"""Returns preprocessing_fn(image, height, width, **kwargs).
Args:
name: The name of the preprocessing function.
is_training: `True` if the model is being used for training and `False`
otherwise.
Returns:
preprocessing_fn: A function that preprocessing a single image (pre-batch).
It has the following signature:
image = preprocessing_fn(image, output_height, output_width, ...).
Raises:
ValueError: If Preprocessing `name` is not recognized.
"""
preprocessing_fn_map = {
'cifarnet': cifarnet_preprocessing,
'inception': inception_preprocessing,
'inception_v1': inception_preprocessing,
'inception_v2': inception_preprocessing,
'inception_v3': inception_preprocessing,
'inception_v4': inception_preprocessing,
'inception_resnet_v2': inception_preprocessing,
'lenet': lenet_preprocessing,
'mobilenet_v1': inception_preprocessing,
'resnet_v1_50': vgg_preprocessing,
'resnet_v1_101': vgg_preprocessing,
'resnet_v1_152': vgg_preprocessing,
'resnet_v1_200': vgg_preprocessing,
'resnet_v2_50': vgg_preprocessing,
'resnet_v2_101': vgg_preprocessing,
'resnet_v2_152': vgg_preprocessing,
'resnet_v2_200': vgg_preprocessing,
'vgg': vgg_preprocessing,
'vgg_a': vgg_preprocessing,
'vgg_16': vgg_preprocessing,
'vgg_19': vgg_preprocessing,
}
if name not in preprocessing_fn_map:
raise ValueError('Preprocessing name [%s] was not recognized' % name)
def preprocessing_fn(image, output_height, output_width, **kwargs):
return preprocessing_fn_map[name].preprocess_image(
image, output_height, output_width, is_training=is_training, **kwargs)
return preprocessing_fn
