def to_tfexample(raw_data, mfcc_data, class_id):
return tf.train.Example(features=tf.train.Features(
feature={
'audio/mfcc': dataset_utils.float_feature(mfcc_data),
'audio/wav/data': dataset_utils.float_feature(raw_data),
'audio/wav/length': dataset_utils.int64_feature(len(raw_data)),
'audio/label': dataset_utils.int64_feature(class_id)
}))
def _process_image(directory, split, name):
# Read the image file.
filename = os.path.join(directory, 'image_2', name + '.png')
image_data = tf.gfile.FastGFile(filename, 'r').read()
# Get shape
img = cv2.imread(filename)
shape = np.shape(img)
label_list = []
type_list = []
bbox_x1_list = []
bbox_y1_list = []
bbox_x2_list = []
bbox_y2_list = []
# If 'test' split, skip annotations
if re.findall(r'train', split):
# Read the txt annotation file.
filename = os.path.join(directory, 'label_2', name + '.txt')
with open(filename) as anno_file:
objects = anno_file.readlines()
for object in objects:
obj_anno = object.split(' ')
type_txt = obj_anno[0].encode('ascii')
if type_txt in CLASSES:
label_list.append(CLASSES[type_txt])
type_list.append(type_txt)
# Bounding Box
bbox_x1 = float(obj_anno[4])
bbox_y1 = float(obj_anno[5])
bbox_x2 = float(obj_anno[6])
bbox_y2 = float(obj_anno[7])
bbox_x1_list.append(bbox_x1)
bbox_y1_list.append(bbox_y1)
bbox_x2_list.append(bbox_x2)
bbox_y2_list.append(bbox_y2)
image_format = b'PNG'
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': bytes_feature(image_data),
'image/height': int64_feature(shape[0]),
'image/width': int64_feature(shape[1]),
'image/channels': int64_feature(shape[2]),
'image/shape': int64_feature(shape),
'image/object/bbox/xmin': float_feature(bbox_x1_list),
'image/object/bbox/xmax': float_feature(bbox_x2_list),
'image/object/bbox/ymin': float_feature(bbox_y1_list),
'image/object/bbox/ymax': float_feature(bbox_y2_list),
'image/object/bbox/label': int64_feature(label_list),
'image/object/bbox/label_text': bytes_feature(type_list),
}))
return example
def to_tfexample(mfcc_data, video_data, class_id):
return tf.train.Example(features=tf.train.Features(
feature={
'audio/mfcc': dataset_utils.float_feature(mfcc_data),
'video/data': dataset_utils.float_feature(video_data),
'label': dataset_utils.int64_feature(class_id)
}))
def to_tfexample(color_data, depth_data,
color_format, depth_format, class_id):
return tf.train.Example(features=tf.train.Features(feature={
'image/color/encoded': dataset_utils.bytes_feature(color_data),
'image/color/format': dataset_utils.bytes_feature(color_format),
'image/depth/encoded': dataset_utils.bytes_feature(depth_data),
'image/depth/format': dataset_utils.bytes_feature(depth_format),
'image/class/label': dataset_utils.int64_feature(class_id),
}))
def to_tfexample(color_video, depth_video, class_id):
return tf.train.Example(features=tf.train.Features(
feature={
'video/color/data': dataset_utils.float_feature(list(color_video)),
'video/color/shape': dataset_utils.float_feature(
color_video.shape),
'video/depth/data': dataset_utils.float_feature(list(depth_video)),
'video/depth/shape': dataset_utils.float_feature(
depth_video.shape),
'video/label': dataset_utils.int64_feature(class_id),
}))
def convert_to_tfrecord(batch, output_file):
images, labels = batch
print('Generating %s' % output_file)
images = images.astype(np.uint8)
labels = labels.astype(np.int64)
with tf.python_io.TFRecordWriter(output_file) as record_writer:
for i in range(len(images)):
example = tf.train.Example(features=tf.train.Features(
feature={
'image': bytes_feature(images[i].tobytes()),
'label': int64_feature(labels[i])
}))
record_writer.write(example.SerializeToString())
def _convert_to_example(image_data, labels, labels_text, bboxes, shape,
difficult, truncated):
"""Build an Example proto for an image example.
Args:
image_data: string, JPEG encoding of RGB image;
labels: list of integers, identifier for the ground truth;
labels_text: list of strings, human-readable labels;
bboxes: list of bounding boxes; each box is a list of integers;
specifying [xmin, ymin, xmax, ymax]. All boxes are assumed to belong
to the same label as the image label.
shape: 3 integers, image shapes in pixels.
Returns:
Example proto
"""
xmin = []
ymin = []
xmax = []
ymax = []
for b in bboxes:
assert len(b) == 4
# pylint: disable=expression-not-assigned
[l.append(point) for l, point in zip([ymin, xmin, ymax, xmax], b)]
# pylint: enable=expression-not-assigned
image_format = b'JPEG'
example = tf.train.Example(features=tf.train.Features(feature={
'image/height': int64_feature(shape[0]),
'image/width': int64_feature(shape[1]),
'image/channels': int64_feature(shape[2]),
'image/shape': int64_feature(shape),
'image/object/bbox/xmin': float_feature(xmin),
'image/object/bbox/xmax': float_feature(xmax),
'image/object/bbox/ymin': float_feature(ymin),
'image/object/bbox/ymax': float_feature(ymax),
'image/object/bbox/label': int64_feature(labels),
'image/object/bbox/label_text': bytes_feature(labels_text),
'image/object/bbox/difficult': int64_feature(difficult),
'image/object/bbox/truncated': int64_feature(truncated),
'image/format': bytes_feature(image_format),
'image/encoded': bytes_feature(image_data)}))
return example