def __init__(self, cfgs):
self.cfgs = cfgs
label_map = LabelMap(cfgs)
self.name_label_map, self.label_name_map = label_map.name2label(), label_map.label2name()
self.NOT_DRAW_BOXES = 0
self.ONLY_DRAW_BOXES = -1
self.ONLY_DRAW_BOXES_WITH_SCORES = -2
self.STANDARD_COLORS = [
'AliceBlue', 'Chartreuse', 'Aqua', 'Aquamarine', 'Azure', 'Beige', 'Bisque',
'BlanchedAlmond', 'BlueViolet', 'BurlyWood', 'CadetBlue', 'AntiqueWhite',
'Chocolate', 'Coral', 'CornflowerBlue', 'Cornsilk', 'Crimson', 'Cyan',
'DarkCyan', 'DarkGoldenRod', 'DarkGrey', 'DarkKhaki', 'DarkOrange',
'DarkOrchid', 'DarkSalmon', 'DarkSeaGreen', 'DarkTurquoise', 'DarkViolet',
'DeepPink', 'DeepSkyBlue', 'DodgerBlue', 'FireBrick', 'FloralWhite',
'ForestGreen', 'Fuchsia', 'Gainsboro', 'GhostWhite', 'Gold', 'GoldenRod',
'Salmon', 'Tan', 'HoneyDew', 'HotPink', 'IndianRed', 'Ivory', 'Khaki',
'Lavender', 'LavenderBlush', 'LawnGreen', 'LemonChiffon', 'LightBlue',
'LightCoral', 'LightCyan', 'LightGoldenRodYellow', 'LightGray', 'LightGrey',
'LightGreen', 'LightPink', 'LightSalmon', 'LightSeaGreen', 'LightSkyBlue',
'LightSlateGray', 'LightSlateGrey', 'LightSteelBlue', 'LightYellow', 'Lime',
'LimeGreen', 'Linen', 'Magenta', 'MediumAquaMarine', 'MediumOrchid',
'MediumPurple', 'MediumSeaGreen', 'MediumSlateBlue', 'MediumSpringGreen',
'MediumTurquoise', 'MediumVioletRed', 'MintCream', 'MistyRose', 'Moccasin',
'NavajoWhite', 'OldLace', 'Olive', 'OliveDrab', 'Orange', 'OrangeRed',
'Orchid', 'PaleGoldenRod', 'PaleGreen', 'PaleTurquoise', 'PaleVioletRed',
'PapayaWhip', 'PeachPuff', 'Peru', 'Pink', 'Plum', 'PowderBlue', 'Purple',
'Red', 'RosyBrown', 'RoyalBlue', 'SaddleBrown', 'Green', 'SandyBrown',
'SeaGreen', 'SeaShell', 'Sienna', 'Silver', 'SkyBlue', 'SlateBlue',
'SlateGray', 'SlateGrey', 'Snow', 'SpringGreen', 'SteelBlue', 'GreenYellow',
'Teal', 'Thistle', 'Tomato', 'Turquoise', 'Violet', 'Wheat', 'White',
'WhiteSmoke', 'Yellow', 'YellowGreen', 'LightBlue', 'LightGreen'
]
self.FONT = ImageFont.load_default()
def read_xml_gtbox_and_label(xml_path):
"""
:param xml_path: the path of voc xml
:return: a list contains gtboxes and labels, shape is [num_of_gtboxes, 9],
and has [x1, y1, x2, y2, x3, y3, x4, y4, label] in a per row
"""
label_map = LabelMap(cfgs)
tree = ET.parse(xml_path)
root = tree.getroot()
img_width = None
img_height = None
box_list = []
for child_of_root in root:
# if child_of_root.tag == 'filename':
# assert child_of_root.text == xml_path.split('/')[-1].split('.')[0] \
# + FLAGS.img_format, 'xml_name and img_name cannot match'
if child_of_root.tag == 'size':
for child_item in child_of_root:
if child_item.tag == 'width':
img_width = int(child_item.text)
if child_item.tag == 'height':
img_height = int(child_item.text)
if child_of_root.tag == 'object':
label = None
for child_item in child_of_root:
if child_item.tag == 'name':
label = label_map.name2label()[child_item.text]
if child_item.tag == 'bndbox':
tmp_box = []
for node in child_item:
tmp_box.append(float(node.text))
assert label is not None, 'label is none, error'
tmp_box.append(label)
box_list.append(tmp_box)
gtbox_label = np.array(box_list, dtype=np.int32)
return img_height, img_width, gtbox_label
def WriterXMLFiles(filename, path, gtbox_label_list, w, h, d):
# dict_box[filename]=json_dict[filename]
doc = xml.dom.minidom.Document()
root = doc.createElement('annotation')
doc.appendChild(root)
foldername = doc.createElement("folder")
foldername.appendChild(doc.createTextNode("JPEGImages"))
root.appendChild(foldername)
nodeFilename = doc.createElement('filename')
nodeFilename.appendChild(doc.createTextNode(filename))
root.appendChild(nodeFilename)
pathname = doc.createElement("path")
pathname.appendChild(doc.createTextNode("xxxx"))
root.appendChild(pathname)
sourcename = doc.createElement("source")
databasename = doc.createElement("database")
databasename.appendChild(doc.createTextNode("Unknown"))
sourcename.appendChild(databasename)
annotationname = doc.createElement("annotation")
annotationname.appendChild(doc.createTextNode("xxx"))
sourcename.appendChild(annotationname)
imagename = doc.createElement("image")
imagename.appendChild(doc.createTextNode("xxx"))
sourcename.appendChild(imagename)
flickridname = doc.createElement("flickrid")
flickridname.appendChild(doc.createTextNode("0"))
sourcename.appendChild(flickridname)
root.appendChild(sourcename)
nodesize = doc.createElement('size')
nodewidth = doc.createElement('width')
nodewidth.appendChild(doc.createTextNode(str(w)))
nodesize.appendChild(nodewidth)
nodeheight = doc.createElement('height')
nodeheight.appendChild(doc.createTextNode(str(h)))
nodesize.appendChild(nodeheight)
nodedepth = doc.createElement('depth')
nodedepth.appendChild(doc.createTextNode(str(d)))
nodesize.appendChild(nodedepth)
root.appendChild(nodesize)
segname = doc.createElement("segmented")
segname.appendChild(doc.createTextNode("0"))
root.appendChild(segname)
label_name_map = LabelMap(cfgs).label2name()
for gtbox_label in gtbox_label_list:
nodeobject = doc.createElement('object')
nodename = doc.createElement('name')
nodename.appendChild(
doc.createTextNode(str(label_name_map[gtbox_label[-1]])))
nodeobject.appendChild(nodename)
nodetruncated = doc.createElement('truncated')
nodetruncated.appendChild(doc.createTextNode(str(0)))
nodeobject.appendChild(nodetruncated)
nodedifficult = doc.createElement('difficult')
nodedifficult.appendChild(doc.createTextNode(str(0)))
nodeobject.appendChild(nodedifficult)
nodepose = doc.createElement('pose')
nodepose.appendChild(doc.createTextNode('xxx'))
nodeobject.appendChild(nodepose)
nodebndbox = doc.createElement('bndbox')
nodex1 = doc.createElement('x1')
nodex1.appendChild(doc.createTextNode(str(gtbox_label[0])))
nodebndbox.appendChild(nodex1)
nodey1 = doc.createElement('y1')
nodey1.appendChild(doc.createTextNode(str(gtbox_label[1])))
nodebndbox.appendChild(nodey1)
nodex2 = doc.createElement('x2')
nodex2.appendChild(doc.createTextNode(str(gtbox_label[2])))
nodebndbox.appendChild(nodex2)
nodey2 = doc.createElement('y2')
nodey2.appendChild(doc.createTextNode(str(gtbox_label[3])))
nodebndbox.appendChild(nodey2)
nodex3 = doc.createElement('x3')
nodex3.appendChild(doc.createTextNode(str(gtbox_label[4])))
nodebndbox.appendChild(nodex3)
nodey3 = doc.createElement('y3')
nodey3.appendChild(doc.createTextNode(str(gtbox_label[5])))
nodebndbox.appendChild(nodey3)
nodex4 = doc.createElement('x4')
nodex4.appendChild(doc.createTextNode(str(gtbox_label[6])))
nodebndbox.appendChild(nodex4)
nodey4 = doc.createElement('y4')
nodey4.appendChild(doc.createTextNode(str(gtbox_label[7])))
nodebndbox.appendChild(nodey4)
# ang = doc.createElement('angle')
# ang.appendChild(doc.createTextNode(str(angle)))
# nodebndbox.appendChild(ang)
nodeobject.appendChild(nodebndbox)
root.appendChild(nodeobject)
fp = open(os.path.join(path, filename), 'w')
doc.writexml(fp, indent='\n')
fp.close()
def __init__(self, cfgs):
self.cfgs = cfgs
self.args = parse_args()
label_map = LabelMap(cfgs)
self.name_label_map, self.label_name_map = label_map.name2label(
), label_map.label2name()
def convert_pascal_to_tfrecord():
"""convert txt (points + label format) to tfrecord
VOC_dir:
--trainval
--images
--labels
--test
--images
--labels
"""
allNeedConvert = ['trainval', 'test']
for train_or_test in allNeedConvert:
label_Path = FLAGS.VOC_dir + "{}/".format(
train_or_test) + FLAGS.txt_dir
image_path = FLAGS.VOC_dir + "{}/".format(
train_or_test) + FLAGS.image_dir
# xml_path = os.path.join(FLAGS.VOC_dir, FLAGS.xml_dir)
# image_path = os.path.join(FLAGS.VOC_dir, FLAGS.image_dir)
print(image_path)
save_path = os.path.join(
FLAGS.save_dir, FLAGS.dataset + '_' + train_or_test + '.tfrecord')
mkdir_or_exist(FLAGS.save_dir)
writer = tf.python_io.TFRecordWriter(path=save_path)
txtFullPathList, _ = get_files(label_Path, _ends=['*.txt'])
for count, txt in enumerate(txtFullPathList):
(txtPath, tmpTxtName) = os.path.split(txt)
(txt_name, extension) = os.path.splitext(tmpTxtName)
img_name = txt_name + FLAGS.img_format
img_path = image_path + '/' + img_name
if not os.path.exists(img_path):
print('{} is not exist!'.format(img_path))
continue
ships = simpletxt_parse(txt, space=' ', boxType='points')
label_map = LabelMap(cfgs)
# print(label_map.name2label())
gtboxes_and_label = []
for ship in ships:
gtbox_label = [0, 0, 0, 0, 0, 0, 0, 0, 0]
gtbox_label[:8] = ship['points']
gtbox_label[8] = label_map.name2label()[ship['label']]
gtboxes_and_label.append(gtbox_label)
img_height, img_width = 1024, 1024
gtboxes_and_label = np.array(gtboxes_and_label, dtype=np.int32)
img = cv2.imread(img_path)[:, :, ::-1]
img = np.array(img, dtype=np.int32)
img_raw = img.tobytes()
num_objects = gtboxes_and_label.shape[0]
# shape = gtboxes_and_label.shape
# gtboxes_and_label=gtboxes_and_label.tobytes()
feature = tf.train.Features(
feature={
# do not need encode() in linux
'img_name':
_bytes_feature(img_name.encode()),
# 'img_name': _bytes_feature(img_name),
'img_height':
_int64_feature(img_height),
'img_width':
_int64_feature(img_width),
'img':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[img_raw])),
'num_objects':
tf.train.Feature(int64_list=tf.train.Int64List(
value=[num_objects])),
'gtboxes_and_label':
_bytes_feature(gtboxes_and_label.tostring())
})
example = tf.train.Example(features=feature)
writer.write(example.SerializeToString())
print('Conversion is complete!save path:{}'.format(
train_or_test, save_path))
writer.close()
def __init__(self, cfgs):
self.cfgs = cfgs
label_map = LabelMap(cfgs)
self.name2label = label_map.name2label()
