def parse_labeled_example(example_proto, view_index, preprocess_fn,
image_attr_keys, label_attr_keys):
"""Parses a labeled test example from a specified view.
Args:
example_proto: A scalar string Tensor.
view_index: Int, index on which view to parse.
preprocess_fn: A function with the signature (raw_images, is_training) ->
preprocessed_images, where raw_images is a 4-D float32 image `Tensor`
of raw images, is_training is a Boolean describing if we're in training,
and preprocessed_images is a 4-D float32 image `Tensor` holding
preprocessed images.
image_attr_keys: List of Strings, names for image keys.
label_attr_keys: List of Strings, names for label attributes.
Returns:
data: A tuple of images, attributes and tasks `Tensors`.
"""
features = {}
for attr_key in image_attr_keys:
features[attr_key] = tf.FixedLenFeature((), tf.string)
for attr_key in label_attr_keys:
features[attr_key] = tf.FixedLenFeature((), tf.int64)
parsed_features = tf.parse_single_example(example_proto, features)
image_only_keys = [i for i in image_attr_keys if 'image' in i]
view_image_key = image_only_keys[view_index]
image = preprocessing.decode_image(parsed_features[view_image_key])
preprocessed = preprocess_fn(image, is_training=False)
attributes = [parsed_features[k] for k in label_attr_keys]
task = parsed_features['task']
return tuple([preprocessed] + attributes + [task])
def parse_labeled_example(
example_proto, view_index, preprocess_fn, image_attr_keys, label_attr_keys):
"""Parses a labeled test example from a specified view.
Args:
example_proto: A scalar string Tensor.
view_index: Int, index on which view to parse.
preprocess_fn: A function with the signature (raw_images, is_training) ->
preprocessed_images, where raw_images is a 4-D float32 image `Tensor`
of raw images, is_training is a Boolean describing if we're in training,
and preprocessed_images is a 4-D float32 image `Tensor` holding
preprocessed images.
image_attr_keys: List of Strings, names for image keys.
label_attr_keys: List of Strings, names for label attributes.
Returns:
data: A tuple of images, attributes and tasks `Tensors`.
"""
features = {}
for attr_key in image_attr_keys:
features[attr_key] = tf.FixedLenFeature((), tf.string)
for attr_key in label_attr_keys:
features[attr_key] = tf.FixedLenFeature((), tf.int64)
parsed_features = tf.parse_single_example(example_proto, features)
image_only_keys = [i for i in image_attr_keys if 'image' in i]
view_image_key = image_only_keys[view_index]
image = preprocessing.decode_image(parsed_features[view_image_key])
preprocessed = preprocess_fn(image, is_training=False)
attributes = [parsed_features[k] for k in label_attr_keys]
task = parsed_features['task']
return tuple([preprocessed] + attributes + [task])
def parse_tf_example(example, is_training, image_size):
features = {
'image/label': tf.FixedLenFeature([], dtype=tf.int64),
'image/encoded': tf.FixedLenFeature([], dtype=tf.string)
}
parsed = tf.parse_single_example(serialized=example, features=features)
label = parsed['image/label']
encode_image = parsed['image/encoded']
# return image of [0,1),shape(?,?,3)
image = preprocessing.decode_image(encode_image)
# return image of [-1,1),need 4-D of input,but shape(?,?,3) is also ok from my test.
image = preprocessing.preprocess_image(
image,
is_training=is_training,
height=image_size[0],
width=image_size[1],
min_scale=0.8,
max_scale=1,
p_scale_up=0.5,
aug_color=True,
)
return image, label