def _convert_to_example(image_data, label):
#print 'shape: {}, height:{}, width:{}'.format(shape,shape[0],shape[1])
example = tf.train.Example(features=tf.train.Features(
feature={
'image/encoded': bytes_feature(image_data),
'label/encoded': bytes_feature(label)
}))
return example
def _convert_to_example(image_data, shape, imname):
#print 'shape: {}, height:{}, width:{}'.format(shape,shape[0],shape[1])
example = tf.train.Example(features=tf.train.Features(
feature={
'image/height': int64_feature(shape[1]),
'image/width': int64_feature(shape[2]),
'image/channels': int64_feature(shape[0]),
'image/shape': int64_feature(shape),
'image/format': bytes_feature('nii'),
'image/encoded': bytes_feature(image_data),
'image/name': bytes_feature(imname),
}))
return example
def _convert_dataset(split_name, filenames, class_names_to_ids, dataset_dir):
"""Converts the given filenames to a TFRecord dataset.
Args:
split_name: The name of the dataset, either 'train' or 'validation'.
filenames: A list of absolute paths to png or jpg images.
class_names_to_ids: A dictionary from class names (strings) to ids
(integers).
dataset_dir: The directory where the converted datasets are stored.
"""
assert split_name in ['train', 'validation']
num_per_shard = int(math.ceil(len(filenames) / float(_NUM_SHARDS))) # ceil:向下取整
with tf.Graph().as_default():
image_reader = ImageReader()
with tf.Session('') as sess:
for shard_id in range(_NUM_SHARDS):
output_filename = _get_dataset_filename(dataset_dir, split_name, shard_id)
with tf.python_io.TFRecordWriter(output_filename) as tfrecord_writer:
start_ndx = shard_id * num_per_shard
end_ndx = min((shard_id+1) * num_per_shard, len(filenames))
for i in range(start_ndx, end_ndx):
sys.stdout.write('\r>> Converting image %d/%d shard %d' % (i+1, len(filenames), shard_id))
sys.stdout.flush()
# Read the filename:
image_data = tf.gfile.FastGFile(filenames[i], 'rb').read()
height, width = image_reader.read_image_dims(sess, image_data)
# 根据路径获得该图片分类
class_name = os.path.basename(os.path.dirname(filenames[i]))
class_id = class_names_to_ids[class_name]
example = tf.train.Example(features=tf.train.Features(feature={
'image/encoded': dataset_utils.bytes_feature(image_data),
'image/format': dataset_utils.bytes_feature(b'jpg'),
'image/class/label': dataset_utils.int64_feature(class_id),
'image/height': dataset_utils.int64_feature(height),
'image/width': dataset_utils.int64_feature(width)}))
tfrecord_writer.write(example.SerializeToString())
sys.stdout.write('\n')
sys.stdout.flush()
def _convert_to_example(image_data, shape, labels, labels_text, bboxes,
filename):
"""Build an Example proto for an image example.
Args:
image_data: string, PNG 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
"""
# Transpose bboxes, dimensions and locations.
bboxes = list(map(list, zip(*bboxes)))
# Iterators.
it_bboxes = iter(bboxes)
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/format': bytes_feature(image_format),
'image/encoded': bytes_feature(image_data),
'image/class/label': int64_feature(labels),
'image/class/text': bytes_feature(labels_text),
'image/object/bbox/xmin': float_feature(next(it_bboxes, [])),
'image/object/bbox/ymin': float_feature(next(it_bboxes, [])),
'image/object/bbox/xmax': float_feature(next(it_bboxes, [])),
'image/object/bbox/ymax': float_feature(next(it_bboxes, [])),
'image/object/class/label': int64_feature(labels),
'image/filename': bytes_feature(filename.encode()),
}))
return example
def _convert_to_example(nc_roi_data,
art_roi_data,
pv_roi_data,
nc_patch_data,
art_patch_data,
pv_patch_data,
label,
attribute_flag=False,
attrs=None):
"""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
"""
if attribute_flag:
image_format = b'JPEG'
# print('attrs is ', attrs)
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),
'images/attrs': float_feature(list(attrs)),
'images/label': int64_feature(label),
'images/nc_roi': bytes_feature(nc_roi_data),
'images/art_roi': bytes_feature(art_roi_data),
'images/pv_roi': bytes_feature(pv_roi_data),
'images/nc_patch': bytes_feature(nc_patch_data),
'images/art_patch': bytes_feature(art_patch_data),
'images/pv_patch': bytes_feature(pv_patch_data),
'images/format': bytes_feature(image_format)
}))
else:
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),
'images/label': int64_feature(label),
'images/nc_roi': bytes_feature(nc_roi_data),
'images/art_roi': bytes_feature(art_roi_data),
'images/pv_roi': bytes_feature(pv_roi_data),
'images/nc_patch': bytes_feature(nc_patch_data),
'images/art_patch': bytes_feature(art_patch_data),
'images/pv_patch': bytes_feature(pv_patch_data),
'images/format': bytes_feature(image_format)
}))
return example
def _convert_to_example(nc_roi_data, art_roi_data, pv_roi_data, nc_patch_data,
art_patch_data, pv_patch_data, attr, label):
"""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
"""
image_format = b'RAW'
# print(np.shape(nc_roi_data), np.shape(art_roi_data), np.shape(pv_roi_data), np.shape(nc_patch_data),
# np.shape(art_patch_data), np.shape(pv_patch_data))
nc_roi_h, nc_roi_w, _ = np.shape(nc_roi_data)
art_roi_h, art_roi_w, _ = np.shape(art_roi_data)
pv_roi_h, pv_roi_w, _ = np.shape(pv_roi_data)
nc_patch_h, nc_patch_w, _ = np.shape(nc_patch_data)
art_patch_h, art_patch_w, _ = np.shape(art_patch_data)
pv_patch_h, pv_patch_w, _ = np.shape(pv_patch_data)
nc_roi_data = np.asarray(nc_roi_data, np.float32)
art_roi_data = np.asarray(art_roi_data, np.float32)
pv_roi_data = np.asarray(pv_roi_data, np.float32)
nc_patch_data = np.asarray(nc_patch_data, np.float32)
art_patch_data = np.asarray(art_patch_data, np.float32)
pv_patch_data = np.asarray(pv_patch_data, np.float32)
# print('np_array_feature')
# print('attrs is ', attrs)
example = tf.train.Example(features=tf.train.Features(
feature={
'images/attrs': float_feature(list(attr)),
'images/label': int64_feature(label),
'images/nc_roi': np_array_feature(nc_roi_data),
'images/nc_roi/shape': int64_feature([nc_roi_h, nc_roi_w, 3]),
'images/art_roi': np_array_feature(art_roi_data),
'images/art_roi/shape': int64_feature([art_roi_h, art_roi_w, 3]),
'images/pv_roi': np_array_feature(pv_roi_data),
'images/pv_roi/shape': int64_feature([pv_roi_h, pv_roi_w, 3]),
'images/nc_patch': np_array_feature(nc_patch_data),
'images/nc_patch/shape': int64_feature([nc_patch_h, nc_patch_w, 3
]),
'images/art_patch': np_array_feature(art_patch_data),
'images/art_patch/shape': int64_feature(
[art_patch_h, art_patch_w, 3]),
'images/pv_patch': np_array_feature(pv_patch_data),
'images/pv_patch/shape': int64_feature([pv_patch_h, pv_patch_w, 3
]),
'images/format': bytes_feature(image_format)
}))
# '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),
return example
