def dict_to_tf_example(image_name,
dataset_directory,
label_map=None,
image_subdirectory='train'):
"""
Args:
image: a single image name
dataset_directory: Path to root directory holding PCam dataset
label_map: A map from string label names to integers ids.
image_subdirectory: String specifying subdirectory within the
PCam dataset directory holding the actual image data.
Returns:
example: The converted tf.Example.
Raises:
ValueError: if the image pointed to by image is not a valid PNG
"""
# full_path = os.path.join(dataset_directory, image_subdirectory, image_name)
full_path = os.path.join(dataset_directory, image_name)
with tf.io.gfile.GFile(full_path, 'rb') as fid:
encoded = fid.read()
encoded_io = io.BytesIO(encoded)
image = Image.open(encoded_io)
width, height = image.size
format = image.format
image_stat = ImageStat.Stat(image)
mean = image_stat.mean
std = image_stat.stddev
key = hashlib.sha256(encoded).hexdigest()
# if image_subdirectory.lower() == 'test':
# label = -1
# else:
# label = int(label_map[image_name])
label = int(label_map[full_path])
example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_utils.int64_feature(height),
'image/width': dataset_utils.int64_feature(width),
'image/filename': dataset_utils.bytes_feature(image_name.encode('utf8')),
'image/fullpath': dataset_utils.bytes_feature(full_path.encode('utf8')),
'image/source_id': dataset_utils.bytes_feature(image_name.encode('utf8')),
'image/key/sha256': dataset_utils.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_utils.bytes_feature(encoded),
'image/format': dataset_utils.bytes_feature(format.encode('utf8')),
'image/class/label': dataset_utils.int64_feature(label),
# 'image/text': dataset_util.bytes_feature('label_text'.encode('utf8'))
'image/mean': dataset_utils.float_list_feature(mean),
'image/std': dataset_utils.float_list_feature(std)
}))
return example
def create_sequence_examples(question, answer, distractors, word_model):
""" Creates multiple sequence examples for distractor encoder model
Args:
question: string containing question
answer: string containing answer
distractors: list of strings containing distractors
Yields:
tf.train.SequenceExample
"""
try:
sampled_negatives = word_model.most_similar_cosmul(
positive=[answer], topn=200)
except KeyError:
return
distractors_lower = set([d.lower() for d in distractors])
sampled_negatives = [
word_model[w] for w, _ in sampled_negatives
if w.lower() not in distractors_lower
][:100]
for d in distractors:
try:
dist_vector = word_model[d]
except KeyError:
continue
question_feature = bytes_feature(question.encode("utf-8"))
answer_feature = bytes_feature(answer.encode("utf-8"))
distractor_feature = float_list_feature(list(dist_vector))
negative_features = [
float_list_feature(list(n)) for n in sampled_negatives
]
context = tf.train.Features(
feature={
"question": question_feature, "answer": answer_feature,
"distractor": distractor_feature,
"negatives_length": int64_feature(len(negative_features)),
}
)
feature_list = {
"negatives": tf.train.FeatureList(feature=negative_features)
}
yield tf.train.SequenceExample(
feature_lists=tf.train.FeatureLists(feature_list=feature_list),
context=context)
def _create_tf_example(image, annotations_list, image_dir):
"""Converts image and annotations to a tf.Example proto.
Args:
image: dict with keys: [u'license', u'file_name', u'coco_url', u'height',
u'width', u'date_captured', u'flickr_url', u'id']
annotations_list:
list of dicts with keys: [u'image_id', u'bbox', u'label',
object[{"category_id", "area", "bbox" : [x,y,width,height],}]]. Notice
that bounding box coordinates in the COCO dataset are given as [x, y,
width, height] tuples using absolute coordinates where x, y represent
the top-left (0-indexed) corner. This function converts to the format
that can be used by the Tensorflow Object Detection API (which is [ymin,
xmin, ymax, xmax] with coordinates normalized relative to image size).
image_dir: directory containing the image files.
Returns:
example: The converted tf.Example
num_annotations_skipped: Number of (invalid) annotations that were ignored.
Raises:
ValueError: if the image pointed to by data['filename'] is not a valid JPEG
"""
image_height = image['height']
image_width = image['width']
filename = image['file_name']
image_id = image['id']
full_path = os.path.join(image_dir, filename)
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
key = hashlib.sha256(encoded_jpg).hexdigest()
xmin = []
xmax = []
ymin = []
ymax = []
category_ids = []
area = []
num_annotations_skipped = 0
label = annotations_list['label']
for object_annotations in annotations_list['object']:
(x, y, width, height) = tuple(object_annotations['bbox'])
if width <= 0 or height <= 0:
num_annotations_skipped += 1
continue
if x + width > image_width or y + height > image_height:
num_annotations_skipped += 1
continue
xmin.append(float(x) / image_width)
xmax.append(float(x + width) / image_width)
ymin.append(float(y) / image_height)
ymax.append(float(y + height) / image_height)
category_id = int(object_annotations['category_id'])
category_ids.append(category_id)
area.append(object_annotations['area'])
feature_dict = {
'image/height':
dataset_utils.int64_feature(image_height),
'image/width':
dataset_utils.int64_feature(image_width),
'image/filename':
dataset_utils.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_utils.bytes_feature(str(image_id).encode('utf8')),
'image/key/sha256':
dataset_utils.bytes_feature(key.encode('utf8')),
'image/encoded':
dataset_utils.bytes_feature(encoded_jpg),
'image/format':
dataset_utils.bytes_feature('jpeg'.encode('utf8')),
'image/class/label':
dataset_utils.int64_feature(label),
'image/object/bbox/xmin':
dataset_utils.float_list_feature(xmin),
'image/object/bbox/xmax':
dataset_utils.float_list_feature(xmax),
'image/object/bbox/ymin':
dataset_utils.float_list_feature(ymin),
'image/object/bbox/ymax':
dataset_utils.float_list_feature(ymax),
'image/object/class/label':
dataset_utils.int64_feature(label),
'image/object/area':
dataset_utils.float_list_feature(area),
}
example = tf.train.Example(features=tf.train.Features(feature=feature_dict))
return key, example, num_annotations_skipped
