def create_tf_example(f, image_path=None):
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
filename = f.readline().rstrip()
filepath = os.path.join(image_path, filename)
image_raw = cv2.imread(filepath)
encoded_image_data = open(filepath, 'rb').read()
key = hashlib.sha256(encoded_image_data).hexdigest()
height, width, channel = image_raw.shape
face_num = int(f.readline().rstrip())
valid_face_num = 0
for i in range(face_num):
annot = f.readline().rstrip().split()
# WIDER FACE DATASET CONTAINS SOME ANNOTATIONS WHAT EXCEEDS THE IMAGE BOUNDARY
if (float(annot[2]) > 25.0):
if (float(annot[3]) > 30.0):
xmins.append(max(0.005, (float(annot[0]) / width)))
ymins.append(max(0.005, (float(annot[1]) / height)))
xmaxs.append(
min(0.995, ((float(annot[0]) + float(annot[2])) / width)))
ymaxs.append(
min(0.995, ((float(annot[1]) + float(annot[3])) / height)))
classes_text.append('face'.encode('utf8'))
classes.append(1)
print(xmins[-1], ymins[-1], xmaxs[-1], ymaxs[-1],
classes_text[-1], classes[-1])
valid_face_num += 1
print("Face Number is %d" % face_num)
print("Valid face number is %d" % valid_face_num)
feature_dict = {
'image/height': dataset_util.int64_feature(int(height)),
'image/width': dataset_util.int64_feature(int(width)),
'image/filename': dataset_util.bytes_feature(filename.encode('utf8')),
# 'image/source_id': dataset_util.bytes_feature(filename.encode('utf8')),
# 'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_image_data),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}
tf_example = tf.train.Example(features=tf.train.Features(
feature=feature_dict))
return valid_face_num, tf_example
def create_tf(input_path,filename,bb_list):
height = size # Image height
width = size # Image width
encoded_image_data = tf.gfile.GFile(input_path+filename).read() # Encoded image bytes
image_format = b'jpeg' # b'jpeg' or b'png'
xmins = [i[0]/float(size) for i in bb_list] # List of normalized left x coordinates in bounding box (1 per box)
xmaxs = [i[1]/float(size) for i in bb_list] # List of normalized right x coordinates in bounding box (1 per box)
ymins = [i[2]/float(size) for i in bb_list] # List of normalized top y coordinates in bounding box (1 per box)
ymaxs = [i[3]/float(size) for i in bb_list] # List of normalized bottom y coordinates in bounding box (1 per box)
classes_text = ['ship'] * len(bb_list) # List of string class name of bounding box (1 per box)
classes = [1] * len(bb_list) # List of integer class id of bounding box (1 per box)
tf_image = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_image_data),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_image
def create_tf_record(image_file, height, width, xmins, ymins, xmaxs, ymaxs, classes_id, classes_text):
'''
param xmins: List of normalized left x coordinates in bounding box (1 per box)
param xmaxs: List of normalized right x coordinates in bounding box (1 per box)
param ymins: List of normalized top y coordinates in bounding box (1 per box)
param ymaxs: List of normalized bottom y coordinates in bounding box (1 per box)
param classes_text: List of string class name of bounding box (1 per box)
param classes: List of integer class id of bounding box (1 per box)
'''
image_data = tf.gfile.FastGFile(image_file, 'rb').read()
encoded_image_data = tf.compat.as_bytes(image_data) # Encoded image bytes
filename = tf.compat.as_bytes(image_file)
image_format = 'png'.encode('utf8') # b'jpeg' or b'png'
tf_single_dataset = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(os.path.basename(filename)),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(image_data),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes_id),
}))
return tf_single_dataset
def create_tf_example(filename, dirpath, boxes):
#Read in the image
with tf.gfile.GFile(os.path.join(dirpath, filename), 'rb') as fid:
encoded_image_data = fid.read()
encoded_jpg_io = io.BytesIO(encoded_image_data)
image = Image.open(encoded_jpg_io)
width, height = image.size
_, ext = os.path.splitext(filename)
image_format = ext[1:].encode('UTF-8') # b'jpeg' or b'png'
xmins = [
x / width for x in boxes['xmins']
] # List of normalized left x coordinates in bounding box (1 per box)
xmaxs = [
x / width for x in boxes['xmaxs']
] # List of normalized right x coordinates in bounding box (1 per box)
ymins = [
y / height for y in boxes['ymins']
] # List of normalized top y coordinates in bounding box (1 per box)
ymaxs = [
y / height for y in boxes['ymaxs']
] # List of normalized bottom y coordinates in bounding box (1 per box)
#DEFAULT LABELS AND CLASSES FOR IVF
classes_text = [b'sperm'] * len(
xmins) # List of string class name of bounding box (1 per box)
classes = [1] * len(
xmins) # List of integer class id of bounding box (1 per box)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename.encode('UTF-8')),
'image/source_id':
dataset_util.bytes_feature(filename.encode('UTF-8')),
'image/encoded':
dataset_util.bytes_feature(encoded_image_data),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def create_tf_example(group, path, labels_mapping):
with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)),
'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
class_idx = labels_mapping.get(row['class'], None)
if class_idx is None:
continue
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['class'].encode('utf8'))
classes.append(class_idx)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename),
'image/source_id':
dataset_util.bytes_feature(filename),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def create_tf_example(group, img_path):
with tf.gfile.GFile(os.path.join(img_path, '{}'.format(group.filename)),
'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
if image.format != 'JPEG':
raise ValueError('Image format not JPEG')
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(row['label'].encode('utf8'))
classes.append(class_text_to_int(row['label']))
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename),
'image/source_id':
dataset_util.bytes_feature(filename),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def create_tf_example(image_file):
print("opening {}".format(image_file))
with tf.gfile.GFile(image_file, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = os.path.basename(image_file).encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
xml_file = image_file + ".xml"
tree = ET.parse(xml_file)
root = tree.getroot()
for member in root.findall('object'):
classes_text.append(member[0].text.encode('utf-8'))
classes.append(class_text_to_int(member[0].text))
xmins.append(int(member[5][0].text) / width)
xmaxs.append(int(member[5][1].text) / width)
ymins.append(int(member[5][2].text) / height)
ymaxs.append(int(member[5][3].text) / height)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename),
'image/source_id':
dataset_util.bytes_feature(filename),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def create_tf_example(image_data):
height = image_data.height # Image height
width = image_data.width # Image width
with tf.gfile.GFile(image_data.path, 'rb') as fid:
encoded_png = fid.read()
filename = image_data.id.encode('utf8')
image_format = b'png' # b'jpeg' or b'png'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for bbox in image_data.bboxes:
xmins.append(bbox.min_x / width)
xmaxs.append(bbox.max_x / width)
ymins.append(bbox.min_y / height)
ymaxs.append(bbox.max_y / height)
classes_text.append(bbox.class_label.encode('utf8'))
classes.append(bbox.class_id)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename),
'image/source_id':
dataset_util.bytes_feature(filename),
'image/encoded':
dataset_util.bytes_feature(encoded_png),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def create_tf_example(example, height, width):
## Udacity's real-life data set
## height = 1096 # Image height
## width = 1368 # Image width
## Udacity's simulator data set
## height = 600
## width = 800
filename = example['filename'] # Filename of the image. Empty if image is not from file
filename = filename.encode()
with tf.gfile.GFile(example['filename'], 'rb') as fid:
encoded_image = fid.read()
image_format = 'jpg'.encode()
xmins = [] # List of normalized left x coordinates in bounding box (1 per box)
xmaxs = [] # List of normalized right x coordinates in bounding box
# (1 per box)
ymins = [] # List of normalized top y coordinates in bounding box (1 per box)
ymaxs = [] # List of normalized bottom y coordinates in bounding box
# (1 per box)
classes_text = [] # List of string class name of bounding box (1 per box)
classes = [] # List of integer class id of bounding box (1 per box)
for box in example['annotations']:
#print("adding box")
xmins.append(float(box['xmin'] / width))
xmaxs.append(float((box['xmin'] + box['x_width']) / width))
ymins.append(float(box['ymin'] / height))
ymaxs.append(float((box['ymin']+ box['y_height']) / height))
classes_text.append(box['class'].encode())
classes.append(int(LABEL_DICT[box['class']]))
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_image),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
def __create_tf_example(frame_data, sorted_label_list):
im = PIL.Image.open(io.BytesIO(frame_data.image))
arr = io.BytesIO()
if frame_data.format == 'jpg':
format = 'JPEG'
else:
format = frame_data.format.upper()
im.save(arr, format=format)
height = im.height
width = im.width
encoded_image_data = arr.getvalue()
rects, labels = bbox_writer.convert_text_to_rects_and_labels(
frame_data.bboxes_text)
# List of normalized coordinates, 1 per box, capped to [0, 1]
xmins = [max(min(rect[0] / width, 1), 0) for rect in rects] # left x
xmaxs = [max(min(rect[2] / width, 1), 0) for rect in rects] # right x
ymins = [max(min(rect[1] / height, 1), 0) for rect in rects] # top y
ymaxs = [max(min(rect[3] / height, 1), 0) for rect in rects] # bottom y
classes_txt = [label.encode('utf-8') for label in labels] # String names
label_to_id_dict = {label: i for i, label in enumerate(sorted_label_list)}
class_ids = [label_to_id_dict[label] for label in labels]
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(frame_data.filename.encode('utf-8')),
'image/source_id':
dataset_util.bytes_feature(frame_data.filename.encode('utf-8')),
'image/encoded':
dataset_util.bytes_feature(encoded_image_data),
'image/format':
dataset_util.bytes_feature(frame_data.format.encode('utf-8')),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_txt),
'image/object/class/label':
dataset_util.int64_list_feature(class_ids),
}))
label_counter_for_frame = collections.Counter(labels)
is_negative = len(rects) == 0
return tf_example, label_counter_for_frame, is_negative
def group_to_tf_record(point, image_directory):
format_png = b'png'
format_jpg = b'jpeg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
class_nums = []
class_ids = []
# changed point[0] to point as is just one point
image_id = point['id']
if image_id.startswith('frame'):
filename = os.path.join(image_directory, image_id + '.png')
format = format_png
else:
filename = os.path.join(image_directory, image_id + '.jpg') #.decode()
format = format_jpg
try:
image = Image.open(filename)
width, height = image.size
with tf.gfile.GFile(filename, 'rb') as fid:
encoded_image = bytes(fid.read())
except:
return None
key = hashlib.sha256(encoded_image).hexdigest()
for anno in point['annotations']:
xmins.append(float(anno['x0']))
xmaxs.append(float(anno['x1']))
ymins.append(float(anno['y0']))
ymaxs.append(float(anno['y1']))
class_nums.append(anno['class_num'])
class_ids.append(bytes(anno['label'].encode('utf8')))
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/filename': dataset_util.bytes_feature(bytes(filename.encode('utf8'))),
'image/source_id': dataset_util.bytes_feature(bytes(image_id.encode('utf8'))),
'image/encoded': dataset_util.bytes_feature(encoded_image),
'image/format': dataset_util.bytes_feature(format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(class_ids),
'image/object/class/label': dataset_util.int64_list_feature(class_nums)
}))
return tf_example
def create_tf_example(filename):
coordinates = filename.rsplit('/', 1)[-1].rsplit('.', 1)[0].split('-')[2]
leftUp, rightDown = [[int(eel) for eel in el.split('&')]
for el in coordinates.split('_')]
xmin, ymin = leftUp
xmax, ymax = rightDown
with tf.gfile.GFile(filename, 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = PIL.Image.open(encoded_jpg_io)
height = image.height
width = image.width
key = hashlib.sha256(encoded_jpg).hexdigest()
ymins = [float(ymin) / height]
xmins = [float(xmin) / width]
ymaxs = [float(ymax) / height]
xmaxs = [float(xmax) / width]
labels_text = ['vehicle plate'.encode('utf8')]
labels = [2]
# print("---------image size:",image.size)
# print("---------xmin:{}, ymin:{}, xmax:{}, ymax:{}".format(xmin,ymin,xmax,ymax))
# print("---------width:{}, height:{}".format(width,height))
feature_dict = {
'image/height': dataset_util.int64_feature(int(height)),
'image/width': dataset_util.int64_feature(int(width)),
'image/filename': dataset_util.bytes_feature(filename.encode('utf8')),
# 'image/source_id': dataset_util.bytes_feature(filename.encode('utf8')),
# 'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(labels_text),
'image/object/class/label': dataset_util.int64_list_feature(labels),
}
example = tf.train.Example(features=tf.train.Features(
feature=feature_dict))
return example
def create_tfdatapoint(file_loc, file, labels):
img = Image.open(os.path.join(file_loc, 'images', file))
(width, height) = img.size
encoded = tf.io.gfile.GFile(os.path.join(file_loc, 'images', file),
"rb").read()
encoded = bytes(encoded)
image_format = b'png'
filename = file.split('.')[0]
data = np.genfromtxt(os.path.join(file_loc, 'labels', filename + '.txt'))
data = data.reshape(int(data.size / 5), 5)
classes = [int(x) for x in data[:, 0]]
classes_text = [labels[x].encode('utf8') for x in classes]
xmins = data[:, 1] - (data[:, 3] / 2.0)
xmaxs = data[:, 1] + (data[:, 3] / 2.0)
ymins = data[:, 2] - (data[:, 4] / 2.0)
ymaxs = data[:, 2] + (data[:, 4] / 2.0)
tf_label_and_data = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(str.encode(filename)),
'image/source_id':
dataset_util.bytes_feature(str.encode(filename)),
'image/encoded':
dataset_util.bytes_feature(encoded),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_label_and_data
def create_tf_example(group, path):
# Opening and readinf the files
with tf.gfile.GFile(os.path.join(path, '{}'.format(group.filename)),
'rb') as fid:
encoded_jpg = fid.read()
# Encode the image in jpeg format to array values
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
# Setting up the image size
width, height = image.size
#Creating the boundary box coordinate instances such as xmin,ymin,xmax,ymax
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'])
xmaxs.append(row['xmax'])
ymins.append(row['ymin'])
ymaxs.append(row['ymax'])
classes.append(row['class'].encode('utf8'))
# This is already exisiting code to convert csv to tfrecord
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/label': dataset_util.bytes_list_feature(
classes),
}))
return tf_example
def dict_to_coco_example(img_data):
"""Convert python dictionary formath data of one image to tf.Example proto.
Args:
img_data: infomation of one image, inclue bounding box, labels of bounding box,\
height, width, encoded pixel data.
Returns:
example: The converted tf.Example
"""
bboxes = img_data['bboxes']
xmin, xmax, ymin, ymax = [], [], [], []
for bbox in bboxes:
xmin.append(bbox[2])
xmax.append(bbox[0])
ymin.append(bbox[3])
ymax.append(bbox[1])
example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(img_data['height']),
'image/width':
dataset_util.int64_feature(img_data['width']),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymax),
'image/object/class/label':
dataset_util.int64_list_feature(img_data['labels']),
'image/object/class/text':
dataset_util.bytes_list_feature(img_data['text']),
'image/encoded':
dataset_util.bytes_feature(img_data['pixel_data']),
'image/format':
dataset_util.bytes_feature('jpeg'.encode('utf-8')),
'image/object/class/file':
dataset_util.bytes_feature(img_data['file'].encode('utf-8')),
}))
return example
def create_tf_example(group, path):
base = os.path.splitext(group.filename)[0]
with tf.gfile.GFile(os.path.join(path, base + ".jpg"), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
filename = group.filename.encode('utf8')
image_format = b'jpg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for index, row in group.object.iterrows():
xmins.append(row['xmin'] / width)
xmaxs.append(row['xmax'] / width)
ymins.append(row['ymin'] / height)
ymaxs.append(row['ymax'] / height)
classes_text.append(int_to_class_text(row['classID']).encode('utf8'))
classes.append(row['classID']+1)
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymaxs),
'image/object/class/text': dataset_util.bytes_list_feature(classes_text),
'image/object/class/label': dataset_util.int64_list_feature(classes),
}))
return tf_example
def dict_to_coco_example(img_data):
"""Convert python dictionary formath data of one image to tf.Example proto.
Args:
img_data: infomation of one image, inclue bounding box, labels of bounding box,\
height, width, encoded pixel data.
Returns:
example: The converted tf.Example
"""
# bboxes = img_data['bboxes']
# xmin, xmax, ymin, ymax = [], [], [], []
# for bbox in bboxes:
# xmin.append(bbox[0])
# xmax.append(bbox[0] + bbox[2])
# ymin.append(bbox[1])
# ymax.append(bbox[1] + bbox[3])
example = tf.train.Example(features=tf.train.Features(feature={
'image/id': dataset_util.int64_feature(img_data['id']),
'image/caption': dataset_util.bytes_list_feature(img_data['caption']),
'image/encoded': dataset_util.bytes_feature(img_data['pixel_data'])
}))
return example
def create_tf_example(height, width, filename, encoded_image_data,
image_format, xmins, xmaxs, ymins, ymaxs, classes_text,
classes):
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height), # Image height
'image/width':
dataset_util.int64_feature(width), # Image width
'image/filename':
dataset_util.bytes_feature(filename), # Filename of the image
'image/source_id':
dataset_util.bytes_feature(filename), # Filename of the image
'image/encoded':
dataset_util.bytes_feature(
encoded_image_data), # Encoded image bytes
'image/format':
dataset_util.bytes_feature(image_format), # b'jpeg' or b'png'
'image/object/bbox/xmin':
dataset_util.float_list_feature(
xmins), # normalized left x coordinate in bounding box
'image/object/bbox/xmax':
dataset_util.float_list_feature(
xmaxs), # normalized right x coordinate in bounding box
'image/object/bbox/ymin':
dataset_util.float_list_feature(
ymins), # normalized top y coordinate in bounding box
'image/object/bbox/ymax':
dataset_util.float_list_feature(
ymaxs), # normalized bottom y coordinate in bounding box
'image/object/class/text':
dataset_util.bytes_list_feature(
classes_text), # string class name of bounding box
'image/object/class/label':
dataset_util.int64_list_feature(
classes), # integer class id of bounding box
}))
return tf_example
def create_tf_example(csv, img_dir):
img_fname = csv[0]
x1, y1, x2, y2 = list(map(int, csv[1:-1]))
cls_idx = int(csv[-1])
cls_text = config.CLASS_NAMES[cls_idx].encode('utf8')
with tf.gfile.GFile(os.path.join(img_dir, img_fname), 'rb') as fid:
encoded_jpg = fid.read()
encoded_jpg_io = io.BytesIO(encoded_jpg)
image = Image.open(encoded_jpg_io)
width, height = image.size
xmin = [x1 / width]
xmax = [x2 / width]
ymin = [y1 / height]
ymax = [y2 / height]
cls_text = [cls_text]
cls_idx = [cls_idx]
filename = img_fname.encode('utf8')
image_format = b'jpg'
tf_example = tf.train.Example(features=tf.train.Features(feature={
'image/height': dataset_util.int64_feature(height),
'image/width': dataset_util.int64_feature(width),
'image/filename': dataset_util.bytes_feature(filename),
'image/source_id': dataset_util.bytes_feature(filename),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/text': dataset_util.bytes_list_feature(cls_text),
'image/object/class/label': dataset_util.int64_list_feature(cls_idx),
}))
return tf_example
def createTFExample(self):
"""Convert XML derived dict to tf.Example proto.
Notice that this function normalizes the bounding box coordinates provided
by the raw data.
Args: None
Returns:
example: The converted tf.Example.
"""
with tf.io.gfile.GFile(self.xml, 'r') as fid:
xml_str = fid.read()
xml = etree.fromstring(xml_str)
data = dataset_util.recursive_parse_xml_to_dict(xml)['annotation']
# the image might be processed in a different location
# so overwrite the path to the input image path for consistency
data['path'] = self.jpg if self.crop == '' else self.__cropImage(data)
print(f"Processing image {data['path']}")
width = int(data['size']['width'])
height = int(data['size']['height'])
filename = data['filename'].encode('utf8')
with tf.io.gfile.GFile(data['path'], 'rb') as fid:
encoded_image_data = fid.read()
image_format = 'jpeg'.encode('utf8')
# List of normalized left x coordinates in bounding box (1 per box)
xmins = []
# List of normalized right x coordinates in bounding box (1 per box)
xmaxs = []
# List of normalized top y coordinates in bounding box (1 per box)
ymins = []
# List of normalized bottom y coordinates in bounding box (1 per box)
ymaxs = []
# List of string class name of bounding box (1 per box)
classes_text = []
classes_id = [] # List of integer class id of bounding box (1 per box)
image = util.loadImage(data['path'])
for obj in data['object']:
if obj['name'] not in classes or not self.__isValidBox(
obj, width, height):
print('Unexpected object: ' + str(obj) + ' in ' + data['path'])
continue
xmins.append(float(obj['bndbox']['xmin']) / width)
ymins.append(float(obj['bndbox']['ymin']) / height)
xmaxs.append(float(obj['bndbox']['xmax']) / width)
ymaxs.append(float(obj['bndbox']['ymax']) / height)
classes_text.append(obj['name'].encode('utf8'))
classes_id.append(getClassID(obj['name']))
util.drawBox(image, self.__encodeBox(obj['bndbox']))
util.saveImage(image,
str(data['path']).replace(".jpg", "-with-boxes.jpg"))
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename),
'image/source_id':
dataset_util.bytes_feature(filename),
'image/encoded':
dataset_util.bytes_feature(encoded_image_data),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes_id),
}))
return tf_example
def read_xml_make_tfrecord():
num_data = 8
for i in range(num_data):
globals()['train_writer_{:05d}-of-{:05d}'.format(
int(i), int(num_data))] = tensorflow.io.TFRecordWriter(
'tfrecord/train/train.tfrecord-{:05d}-of-{:05d}'.format(
int(i), int(num_data)))
for i in range(int(num_data / 8)):
globals()['test_writer_{:05d}-of-{:05d}'.format(
int(i), int(num_data / 8))] = tensorflow.io.TFRecordWriter(
'tfrecord/test/test.tfrecord-{:05d}-of-{:05d}'.format(
int(i), int(num_data / 8)))
globals()['valid_writer_{:05d}-of-{:05d}'.format(
int(i), int(num_data / 8))] = tensorflow.io.TFRecordWriter(
'tfrecord/valid/valid.tfrecord-{:05d}-of-{:05d}'.format(
int(i), int(num_data / 8)))
length = len(os.listdir(folder))
for number, img_name in enumerate(os.listdir(folder)):
if img_name[-4:] != '.jpg': continue
filename = img_name[:-4]
img = cv2.imread(folder + filename + ".jpg")
height, width = img.shape[:2]
mask = cv2.imread('mask/' + filename + '.jpg', 0)
mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, np.ones((5, 5),
np.uint8))
cv2.imshow("asdas", mask)
cv2.waitKey()
_, contours, _ = cv2.findContours(mask, cv2.RETR_TREE,
cv2.CHAIN_APPROX_SIMPLE)
print(contours)
contours = sorted(contours, key=lambda x: len(x), reverse=True)
x = [temp[0][0] for temp in contours[0]]
y = [temp[0][1] for temp in contours[0]]
xmin = min(x)
xmax = max(x)
ymin = min(y)
ymax = max(y)
# cv2.circle(img,(xmin,ymin),5,(255,0,0),5)
# cv2.circle(img, (xmax, ymax), 5, (255, 0, 0), 5)
# cv2.imshow("asd",img)
# cv2.waitKey()
object_name = 'passport'
pixel_val = 255
with tensorflow.io.gfile.GFile(folder + filename + ".jpg",
'rb') as fid:
encoded_image_data = fid.read()
key = hashlib.sha256(encoded_image_data).hexdigest()
with tensorflow.io.gfile.GFile('mask/' + filename + ".jpg",
'rb') as fid:
encoded_mask_data = fid.read()
encoded_mask = io.BytesIO(encoded_mask_data)
mask = Image.open(encoded_mask)
mask_np = np.asarray(mask.convert('L'))
mask_remapped = (mask_np == pixel_val).astype(np.uint8)
# print("mask",mask_remapped.shape)
# cv2.imshow("asd",mask_remapped*255)
# cv2.waitKey()
mask_img = Image.fromarray(mask_remapped)
output = io.BytesIO()
mask_img.save(output, format='PNG')
xmins = [xmin / width]
xmaxs = [xmax / width]
ymins = [ymin / height]
ymaxs = [ymax / height]
classes_text = [object_name.encode('utf8')]
classes = [1]
masks = [output.getvalue()]
print(img_name)
print(xmins)
print(xmaxs)
print(ymins)
print(ymaxs)
print(classes_text)
print(classes)
print(masks)
example = tensorflow.train.Example(features=tensorflow.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(img_name.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(img_name.encode('utf8')),
'image/key/sha256':
dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_image_data),
'image/format':
dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
'image/object/mask':
dataset_util.bytes_list_feature(masks),
}))
if number < length * 0.8:
globals()['train_writer_{:05d}-of-{:05d}'.format(
int(number / (length * 0.8) * num_data),
int(num_data))].write(example.SerializeToString())
elif number < length * 0.9:
globals()['valid_writer_{:05d}-of-{:05d}'.format(
int((number - length * 0.8) / (length * 0.1) * num_data / 8),
int(num_data / 8))].write(example.SerializeToString())
elif number < length:
globals()['test_writer_{:05d}-of-{:05d}'.format(
int((number - length * 0.9) / (length * 0.1) * num_data / 8),
int(num_data / 8))].write(example.SerializeToString())
def xml_to_tf(path_input, path_output):
xml_list = []
column_name = [
'filename', 'width', 'height', 'class', 'xmin', 'ymin', 'xmax', 'ymax'
]
print(path_output)
writer = tf.io.TFRecordWriter(path_output)
files = os.listdir(path_input)
for file in files:
if file.endswith(".xml"):
xmlFile = path_input + file
tree = ET.parse(xmlFile)
root = tree.getroot()
filename = root[1].text
width = int(root[4][0].text)
height = int(root[4][1].text)
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for member in root.findall('object'):
beer = member[0].text
xmin = int(member[4][0].text)
ymin = int(member[4][1].text)
xmax = int(member[4][2].text)
ymax = int(member[4][3].text)
xmins.append(xmin / width)
xmaxs.append(xmax / width)
ymins.append(ymin / height)
ymaxs.append(ymax / height)
classes_text.append(beer.encode('utf8'))
classes.append(class_text_to_int(beer))
with tf.io.gfile.GFile(
os.path.join(path_input, '{}'.format(filename)),
'rb') as fid:
encoded_jpg = fid.read()
print(encoded_jpg)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature(IMAGE_FORMAT),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
writer.write(tf_example.SerializeToString())
writer.close()
output_path = os.path.join(os.getcwd(), path_output)
print('Successfully created the TFRecords: {}'.format(output_path))
def create_tf_example(image,
annotations_list,
image_dir,
category_index,
include_masks=False):
"""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'segmentation', u'area', u'iscrowd', u'image_id',
u'bbox', u'category_id', u'id']
Notice that bounding box coordinates in the official 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 expected by the Tensorflow Object Detection API (which is
which is [ymin, xmin, ymax, xmax] with coordinates normalized relative
to image size).
image_dir: directory containing the image files.
category_index: a dict containing COCO category information keyed
by the 'id' field of each category. See the
label_map_util.create_category_index function.
include_masks: Whether to include instance segmentations masks
(PNG encoded) in the result. default: False.
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()
key = hashlib.sha256(encoded_jpg).hexdigest()
xmin = []
xmax = []
ymin = []
ymax = []
is_crowd = []
category_names = []
category_ids = []
area = []
encoded_mask_png = []
num_annotations_skipped = 0
for object_annotations in annotations_list:
(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)
is_crowd.append(object_annotations['iscrowd'])
category_id = int(object_annotations['category_id'])
category_ids.append(category_id)
category_names.append(
category_index[category_id]['name'].encode('utf8'))
area.append(object_annotations['area'])
if include_masks:
run_len_encoding = mask.frPyObjects(
object_annotations['segmentation'], image_height, image_width)
binary_mask = mask.decode(run_len_encoding)
if not object_annotations['iscrowd']:
binary_mask = np.amax(binary_mask, axis=2)
pil_image = PIL.Image.fromarray(binary_mask)
output_io = io.BytesIO()
pil_image.save(output_io, format='PNG')
encoded_mask_png.append(output_io.getvalue())
feature_dict = {
'image/height': dataset_util.int64_feature(image_height),
'image/width': dataset_util.int64_feature(image_width),
'image/filename': dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(str(image_id).encode('utf8')),
'image/key/sha256': dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded': dataset_util.bytes_feature(encoded_jpg),
'image/format': dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin': dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax': dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin': dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax': dataset_util.float_list_feature(ymax),
'image/object/class/text':
dataset_util.bytes_list_feature(category_names),
'image/object/is_crowd': dataset_util.int64_list_feature(is_crowd),
'image/object/area': dataset_util.float_list_feature(area),
}
if include_masks:
feature_dict['image/object/mask'] = (
dataset_util.bytes_list_feature(encoded_mask_png))
example = tf.train.Example(features=tf.train.Features(
feature=feature_dict))
return key, example, num_annotations_skipped
def create_tf_example(filename, label_file):
img = cv2.imread(filename)
height, width, channels = img.shape
with tf.gfile.GFile(filename, 'rb') as fid:
encoded_image_data = fid.read()
image_format = b'jpg'
xmins = [
] # List of normalized left x coordinates in bounding box (1 per box)
xmaxs = [] # List of normalized right x coordinates in bounding box
# (1 per box)
ymins = [
] # List of normalized top y coordinates in bounding box (1 per box)
ymaxs = [] # List of normalized bottom y coordinates in bounding box
# (1 per box)
classes_text = [] # List of string class name of bounding box (1 per box)
classes = [] # List of integer class id of bounding box (1 per box)
with open(label_file, 'r') as f:
csvreader = csv.reader(f, delimiter=' ')
head = True
for row in csvreader:
if head:
head = False
continue
name = row[-1]
classes_text.append(name)
classes.append(get_index(name))
xmins.append(float(row[0]) / width)
xmaxs.append(float(row[2]) / width)
ymins.append(float(row[1]) / height)
ymaxs.append(float(row[3]) / height)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename),
'image/source_id':
dataset_util.bytes_feature(filename),
'image/encoded':
dataset_util.bytes_feature(encoded_image_data),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def _create_tf_entry(self, categories, img, label, filename, annotations):
imageFormat = b'jpg'
width, height = img.size
imgByteArr = io.BytesIO()
img.save(imgByteArr, format='JPEG')
encodedImageData = imgByteArr.getvalue()
xmins = []
xmaxs = []
ymins = []
ymaxs = []
for annotation in annotations:
rect = None
if type(
annotation.data
) is Rectangle: #currently we only support Rect annotations, TODO: change me
rect = annotation.data
elif type(annotation.data) is Polygon:
rect = annotation.data.rect
if rect is not None:
trimmed_rect = rect.trim(
Rectangle(0, 0, width, height)
) #scale to image dimension in case annotation exceeds image width/height
if trimmed_rect.left < 0:
raise ImageMonkeyGeneralError(
"trimmed rect left dimension invalid! (<0)")
if trimmed_rect.top < 0:
raise ImageMonkeyGeneralError(
"trimmed rect top dimension invalid! (<0)")
if trimmed_rect.width < 0:
raise ImageMonkeyGeneralError(
"trimmed rect width dimension invalid! (<0)")
if trimmed_rect.height < 0:
raise ImageMonkeyGeneralError(
"trimmed rect height dimension invalid! (<0)")
if (trimmed_rect.left + trimmed_rect.width) > width:
raise ImageMonkeyGeneralError(
"bounding box width > image width!")
if (trimmed_rect.top + trimmed_rect.height) > height:
raise ImageMonkeyGeneralError(
"bounding box height > image height!")
xmin = trimmed_rect.left / float(width)
xmax = (trimmed_rect.left + trimmed_rect.width) / float(width)
ymin = trimmed_rect.top / float(height)
ymax = (trimmed_rect.top + trimmed_rect.height) / float(height)
#sanity checks
if xmin > xmax:
raise ImageMonkeyGeneralError("xmin > xmax!")
if ymin > ymax:
raise ImageMonkeyGeneralError("ymin > ymax!")
if (xmin == 0) and (xmax == 0) and (ymin == 0) and (ymax == 0):
continue #skip bounding boxes that are 0
xmins.append(xmin)
xmaxs.append(xmax)
ymins.append(ymin)
ymaxs.append(ymax)
#we might have some images in our dataset, which don't have a annotation, skip those
if ((len(xmins) == 0) or (len(xmaxs) == 0) or (len(ymins) == 0)
or (len(ymaxs) == 0)):
return None
classes = [(categories.index(label) + 1)] * len(
xmins) #class indexes start with 1
labels = [label.encode('utf8')] * len(xmins)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename.encode()),
'image/source_id':
dataset_util.bytes_feature(filename.encode()),
'image/encoded':
dataset_util.bytes_feature(encodedImageData),
'image/format':
dataset_util.bytes_feature(imageFormat),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(labels),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def dict_to_tf_example(data,
image_path,
label_map_dict,
ignore_difficult_instances=False,
image_subdirectory='images'):
"""Convert XML derived dict to tf.Example proto.
Notice that this function normalizes the bounding box coordinates provided
by the raw data.
Args:
data: dict holding PASCAL XML fields for a single image (obtained by
running dataset_util.recursive_parse_xml_to_dict)
image_path: Full path to image file
label_map_dict: A map from string label names to integers ids.
ignore_difficult_instances: Whether to skip difficult instances in the
dataset (default: False).
image_subdirectory: String specifying subdirectory within the
PASCAL dataset directory holding the actual image data.
Returns:
example: The converted tf.Example.
Raises:
ValueError: if the image pointed to by data['filename'] is not a valid JPEG
"""
# img_path = os.path.join(
# data['folder'], image_subdirectory, data['filename'])
# full_path = os.path.join(dataset_directory, img_path)
full_path = image_path
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)
if image.format != 'JPEG':
raise ValueError('Image format not JPEG')
key = hashlib.sha256(encoded_jpg).hexdigest()
width = int(data['size']['width'])
height = int(data['size']['height'])
filename = full_path.split('/')[-1]
xmin = []
ymin = []
xmax = []
ymax = []
classes = []
classes_text = []
truncated = []
poses = []
difficult_obj = []
if 'object' in data:
for obj in data['object']:
difficult = False # bool(int(obj['difficult']))
if ignore_difficult_instances and difficult:
continue
difficult_obj.append(int(difficult))
xmin.append(float(obj['bndbox']['xmin']) / width)
ymin.append(float(obj['bndbox']['ymin']) / height)
xmax.append(float(obj['bndbox']['xmax']) / width)
ymax.append(float(obj['bndbox']['ymax']) / height)
classes_text.append(obj['name'].encode('utf8'))
classes.append(label_map_dict[obj['name']])
# truncated.append(int(obj['truncated']))
truncated.append(0)
# poses.append(obj['pose'].encode('utf8'))
example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/key/sha256':
dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymax),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
'image/object/difficult':
dataset_util.int64_list_feature(difficult_obj),
'image/object/truncated':
dataset_util.int64_list_feature(truncated),
'image/object/view':
dataset_util.bytes_list_feature(poses),
}))
return example
def background_tf_example(image_path, ):
"""
Args:
image_path: Full path to image file
Returns:
example: The converted tf.Example.
"""
full_path = image_path
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)
if image.format != 'JPEG':
raise ValueError('Image format not JPEG')
key = hashlib.sha256(encoded_jpg).hexdigest()
filename = full_path.split('/')[-1]
width = image.width
height = image.height
xmin = []
ymin = []
xmax = []
ymax = []
classes = []
classes_text = []
truncated = []
poses = []
difficult_obj = []
example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/key/sha256':
dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymax),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
'image/object/difficult':
dataset_util.int64_list_feature(difficult_obj),
'image/object/truncated':
dataset_util.int64_list_feature(truncated),
'image/object/view':
dataset_util.bytes_list_feature(poses),
}))
return example
def create_tf_example(image,
image_dir,
bbox_annotations=None,
category_index=None,
include_mask=False):
"""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', u'not_exhaustive_category_ids',
u'neg_category_ids']
image_dir: directory containing the image files.
bbox_annotations:
list of dicts with keys:
[u'segmentation', u'area', u'image_id', u'bbox', u'category_id', u'id']
Notice that bounding box coordinates in the official LVIS 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 expected by the Tensorflow Object Detection API (which is
which is [ymin, xmin, ymax, xmax] with coordinates normalized relative
to image size).
category_index: a dict containing LVIS category information keyed
by the 'id' field of each category. See the
label_map_util.create_category_index function.
include_mask: Whether to include instance segmentations masks
(PNG encoded) in the result. default: False.
Returns:
success: whether the conversion is successful
filename: image filename
example: The converted tf.Example
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['coco_url']
filename = osp.join(*filename.split('/')[-2:])
image_id = image['id']
image_not_exhaustive_category_ids = image['not_exhaustive_category_ids']
image_neg_category_ids = image['neg_category_ids']
full_path = os.path.join(image_dir, filename)
if not tf.gfile.Exists(full_path):
tf.logging.warn(f'image {full_path} not exists! skip')
return False, None, None
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
key = hashlib.sha256(encoded_jpg).hexdigest()
feature_dict = {
'image/height':
dataset_util.int64_feature(image_height),
'image/width':
dataset_util.int64_feature(image_width),
'image/filename':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(str(image_id).encode('utf8')),
'image/key/sha256':
dataset_util.bytes_feature(key.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature('jpeg'.encode('utf8')),
'image/not_exhaustive_category_ids':
dataset_util.int64_list_feature(image_not_exhaustive_category_ids),
'image/image_neg_category_ids':
dataset_util.int64_list_feature(image_neg_category_ids),
}
if bbox_annotations:
xmin = []
xmax = []
ymin = []
ymax = []
is_crowd = []
category_names = []
category_ids = []
area = []
encoded_mask_png = []
for object_annotations in bbox_annotations:
(x, y, width, height) = tuple(object_annotations['bbox'])
xmin_single = max(float(x) / image_width, 0.0)
xmax_single = min(float(x + width) / image_width, 1.0)
ymin_single = max(float(y) / image_height, 0.0)
ymax_single = min(float(y + height) / image_height, 1.0)
if xmax_single <= xmin_single or ymax_single <= ymin_single:
continue
xmin.append(xmin_single)
xmax.append(xmax_single)
ymin.append(ymin_single)
ymax.append(ymax_single)
is_crowd.append(0)
category_id = int(object_annotations['category_id'])
category_ids.append(category_id)
category_names.append(
category_index[category_id]['name'].encode('utf8'))
area.append(object_annotations['area'])
if include_mask:
run_len_encoding = mask.frPyObjects(
object_annotations['segmentation'], image_height,
image_width)
binary_mask = mask.decode(run_len_encoding)
binary_mask = np.amax(binary_mask, axis=2)
pil_image = PIL.Image.fromarray(binary_mask)
output_io = io.BytesIO()
pil_image.save(output_io, format='PNG')
encoded_mask_png.append(output_io.getvalue())
feature_dict.update({
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmin),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmax),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymin),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymax),
'image/object/class/text':
dataset_util.bytes_list_feature(category_names),
'image/object/class/label':
dataset_util.int64_list_feature(category_ids),
'image/object/is_crowd':
dataset_util.int64_list_feature(is_crowd),
'image/object/area':
dataset_util.float_list_feature(area),
})
if include_mask:
feature_dict['image/object/mask'] = (
dataset_util.bytes_list_feature(encoded_mask_png))
example = tf.train.Example(features=tf.train.Features(
feature=feature_dict))
return True, filename, example
def create_tf_example(image,
annotations_list,
image_dir,
category_index,
include_masks=False):
# image_height = image[2]
# image_width = image[1]
# filename = image[0]# TODO(user): Populate the following variables from your example.
# print(image)
height = image['height'] # Image height
width = image['width'] # Image width
filename = image[
'filename'] # Filename of the image. Empty if image is not from file
full_path = os.path.join(image_dir, filename)
with tf.gfile.GFile(full_path, 'rb') as fid:
encoded_jpg = fid.read()
encoded_image_io = io.BytesIO(encoded_jpg) # Encoded image bytes
image = PIL.Image.open(encoded_image_io)
only_file_name, image_format = os.path.splitext(filename)
xmins = [
] # List of normalized left x coordinates in bounding box (1 per box)
xmaxs = [] # List of normalized right x coordinates in bounding box
# (1 per box)
ymins = [
] # List of normalized top y coordinates in bounding box (1 per box)
ymaxs = [] # List of normalized bottom y coordinates in bounding box
# (1 per bo)
classes_text = [] # List of string class name of bounding box (1 per box)
classes = [] # List of integer class id of bounding box (1 per box)
# print(len(annotations_list))
for annotation in annotations_list:
# print(annotation)
xmins.append(annotation['xmin'] / width)
xmaxs.append(annotation['xmax'] / width)
ymins.append(annotation['ymin'] / height)
ymaxs.append(annotation['ymax'] / height)
classes_text.append(annotation['label_text'].encode('utf8'))
classes.append(annotation['label'])
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/source_id':
dataset_util.bytes_feature(filename.encode('utf8')),
'image/encoded':
dataset_util.bytes_feature(encoded_jpg),
'image/format':
dataset_util.bytes_feature(image_format.encode('utf8')),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
return tf_example
def json_to_record(j):
assert (len(j["image_size"]) == 1)
assert (len(j["categories"]) == len(j["annotations"]))
image_size = j["image_size"][0]
height = image_size["height"]
width = image_size["width"]
filename = os.path.basename(j["file"])
# actual image bytes? refer to dataset_tools/create_pet_tf_record.py
with tf.gfile.GFile(j["file"], "rb") as fid:
encoded_jpg = fid.read()
pass
encoded_image_data = encoded_jpg
image_format = b'jpeg'
xmins = []
xmaxs = []
ymins = []
ymaxs = []
classes_text = []
classes = []
for annot in j["annotations"]:
c_name = class_id_to_name(annot["class_id"])
classes_text.append(c_name.encode("utf8"))
# class_ids are indexed by 1 for tensorflow
classes.append(annot["class_id"] + 1)
corners = get_box_corners(annot)
xmins.append(corners["xmin"] / width)
xmaxs.append(corners["xmax"] / width)
ymins.append(corners["ymin"] / height)
ymaxs.append(corners["ymax"] / height)
tf_example = tf.train.Example(features=tf.train.Features(
feature={
'image/height':
dataset_util.int64_feature(height),
'image/width':
dataset_util.int64_feature(width),
'image/filename':
dataset_util.bytes_feature(filename.encode("utf8")),
'image/source_id':
dataset_util.bytes_feature(filename.encode("utf8")),
'image/encoded':
dataset_util.bytes_feature(encoded_image_data),
'image/format':
dataset_util.bytes_feature(image_format),
'image/object/bbox/xmin':
dataset_util.float_list_feature(xmins),
'image/object/bbox/xmax':
dataset_util.float_list_feature(xmaxs),
'image/object/bbox/ymin':
dataset_util.float_list_feature(ymins),
'image/object/bbox/ymax':
dataset_util.float_list_feature(ymaxs),
'image/object/class/text':
dataset_util.bytes_list_feature(classes_text),
'image/object/class/label':
dataset_util.int64_list_feature(classes),
}))
# print(tf_example)
return tf_example
pass