def parse_record(raw_record, is_training):
"""Parses a record containing a training example of an image.
The input record is parsed into a label and image, and the image is passed
through preprocessing steps (cropping, flipping, and so on).
Args:
raw_record: scalar Tensor tf.string containing a serialized
Example protocol buffer.
is_training: A boolean denoting whether the input is for training.
Returns:
Tuple with processed image tensor and one-hot-encoded label tensor.
"""
#print(" I am here in parse_record function in imagenet_main")
image_buffer, label, bbox = _parse_example_proto(raw_record)
image = imagenet_preprocessing.preprocess_image(
image_buffer=image_buffer,
bbox=bbox,
output_height=_DEFAULT_IMAGE_SIZE,
output_width=_DEFAULT_IMAGE_SIZE,
num_channels=_NUM_CHANNELS,
is_training=is_training)
#print(" I am here in parse_record function in imagenet_main, image and label created")
return image, label
def parse_record(raw_record, is_training, dtype):
"""Parses a record containing a training example of an image.
The input record is parsed into a label and image, and the image is passed
through preprocessing steps (cropping, flipping, and so on).
Args:
raw_record: scalar Tensor tf.string containing a serialized
Example protocol buffer.
is_training: A boolean denoting whether the input is for training.
dtype: data type to use for images/features.
Returns:
Tuple with processed image tensor and one-hot-encoded label tensor.
"""
image_buffer, label, bbox = _parse_example_proto(raw_record)
image = imagenet_preprocessing.preprocess_image(
image_buffer=image_buffer,
bbox=bbox,
output_height=DEFAULT_IMAGE_SIZE,
output_width=DEFAULT_IMAGE_SIZE,
num_channels=NUM_CHANNELS,
is_training=is_training)
image = tf.cast(image, dtype)
return image, label
def preprocess(self, image_buffer, bbox, batch_position):
# pylint: disable=g-import-not-at-top
try:
from official.resnet.imagenet_preprocessing import preprocess_image
except ImportError:
tf.logging.fatal('Please include tensorflow/models to the PYTHONPATH.')
raise
if self.train:
image = preprocess_image(
image_buffer, bbox, self.height, self.width, self.depth,
is_training=True)
else:
image = preprocess_image(
image_buffer, bbox, self.height, self.width, self.depth,
is_training=False)
return tf.cast(image, self.dtype)
def parse_record(raw_record, is_training):
"""Parses a record containing a training example of an image.
The input record is parsed into a label and image, and the image is passed
through preprocessing steps (cropping, flipping, and so on).
Args:
raw_record: scalar Tensor tf.string containing a serialized
Example protocol buffer.
is_training: A boolean denoting whether the input is for training.
Returns:
Tuple with processed image tensor and one-hot-encoded label tensor.
"""
image_buffer, label, bbox = _parse_example_proto(raw_record)
image = imagenet_preprocessing.preprocess_image(
image_buffer=image_buffer,
bbox=bbox,
output_height=_DEFAULT_IMAGE_SIZE,
output_width=_DEFAULT_IMAGE_SIZE,
num_channels=_NUM_CHANNELS,
is_training=is_training)
return image, label
def preprocess_image(file_name, output_height=224, output_width=224,
num_channels=3):
"""Run standard ImageNet preprocessing on the passed image file.
Args:
file_name: string, path to file containing a JPEG image
output_height: int, final height of image
output_width: int, final width of image
num_channels: int, depth of input image
Returns:
Float array representing processed image with shape
[output_height, output_width, num_channels]
Raises:
ValueError: if image is not a JPEG.
"""
if imghdr.what(file_name) != "jpeg":
raise ValueError("At this time, only JPEG images are supported. "
"Please try another image.")
image_buffer = tf.read_file(file_name)
normalized = imagenet_preprocessing.preprocess_image(
image_buffer=image_buffer,
bbox=None,
output_height=output_height,
output_width=output_width,
num_channels=num_channels,
is_training=False)
with tf.Session(config=get_gpu_config()) as sess:
result = sess.run([normalized])
return result[0]
def preprocess_image(file_name, output_height=224, output_width=224,
num_channels=3):
"""Run standard ImageNet preprocessing on the passed image file.
Args:
file_name: string, path to file containing a JPEG image
output_height: int, final height of image
output_width: int, final width of image
num_channels: int, depth of input image
Returns:
Float array representing processed image with shape
[output_height, output_width, num_channels]
Raises:
ValueError: if image is not a JPEG.
"""
if imghdr.what(file_name) != "jpeg":
raise ValueError("At this time, only JPEG images are supported. "
"Please try another image.")
image_buffer = tf.read_file(file_name)
normalized = imagenet_preprocessing.preprocess_image(
image_buffer=image_buffer,
bbox=None,
output_height=output_height,
output_width=output_width,
num_channels=num_channels,
is_training=False)
with tf.Session(config=get_gpu_config()) as sess:
result = sess.run([normalized])
return result[0]
def _preprocess_image(image_bytes):
"""Preprocess a single raw image."""
# Bounding box around the whole image.
bbox = tf.constant([0.0, 0.0, 1.0, 1.0], dtype=dtype, shape=[1, 1, 4])
height, width, num_channels = image_shape
image = imagenet_preprocessing.preprocess_image(
image_bytes, bbox, height, width, num_channels, is_training=False)
return image
def _preprocess_image(image_bytes):
"""Preprocess a single raw image."""
# Bounding box around the whole image.
bbox = tf.constant([0.0, 0.0, 1.0, 1.0], dtype=dtype, shape=[1, 1, 4])
height, width, num_channels = image_shape
image = imagenet_preprocessing.preprocess_image(
image_bytes, bbox, height, width, num_channels, is_training=False)
return image
def _parse_function(example_proto, output_height, output_width, is_training=False,
resize_side_min=_RESIZE_SIDE_MIN):
"""Parse TF Records and preprocess image and labels
"""
# parse the TFRecord
feature_map = {
"image/encoded": tf.FixedLenFeature((), tf.string, default_value=""),
"image/format": tf.FixedLenFeature((), tf.string, default_value=""),
"image/class/label": tf.VarLenFeature(tf.int64),
"image/height": tf.FixedLenFeature((), tf.int64, default_value=0),
"image/width": tf.FixedLenFeature((), tf.int64, default_value=0),
"image/object/bbox/xmin": tf.VarLenFeature(tf.float32),
"image/object/bbox/ymin": tf.VarLenFeature(tf.float32),
"image/object/bbox/xmax": tf.VarLenFeature(tf.float32),
"image/object/bbox/ymax": tf.VarLenFeature(tf.float32),
}
features = tf.parse_single_example(example_proto, feature_map)
# parse bounding box
xmin = tf.expand_dims(features['image/object/bbox/xmin'].values, 0)
ymin = tf.expand_dims(features['image/object/bbox/ymin'].values, 0)
xmax = tf.expand_dims(features['image/object/bbox/xmax'].values, 0)
ymax = tf.expand_dims(features['image/object/bbox/ymax'].values, 0)
bbox = tf.concat([ymin, xmin, ymax, xmax], 0)
bbox = tf.expand_dims(bbox, 0)
bbox = tf.transpose(bbox, [0, 2, 1])
# ImageNet preprocessing
from official.resnet import imagenet_preprocessing
image = imagenet_preprocessing.preprocess_image(
image_buffer=features["image/encoded"],
bbox=bbox,
output_height=output_height,
output_width=output_width,
num_channels=_NUM_CHANNELS,
is_training=is_training)
# convert labels to dense
labels = tf.sparse_tensor_to_dense(features["image/class/label"])
return image, labels
