path = os.path.join(os.path.dirname(__file__),
'VOCdevkit-matlab-wrapper')
cmd = 'cd {} && '.format(path)
cmd += '{:s} -nodisplay -nodesktop '.format(datasets.MATLAB)
cmd += '-r "dbstop if error; '
cmd += 'voc_eval(\'{:s}\',\'{:s}\',\'{:s}\',\'{:s}\',{:d}); quit;"' \
.format(self._devkit_path, comp_id,
self._image_set, output_dir, int(rm_results))
print('Running:\n{}'.format(cmd))
status = subprocess.call(cmd, shell=True)
def evaluate_detections(self, all_boxes, output_dir):
comp_id = self._write_voc_results_file(all_boxes)
# self._do_matlab_eval(comp_id, output_dir)
def competition_mode(self, on):
if on:
self.config['use_salt'] = False
self.config['cleanup'] = False
else:
self.config['use_salt'] = True
self.config['cleanup'] = True
if __name__ == '__main__':
d = datasets.kitti('trainval')
res = d.roidb
from IPython import embed
embed()
for cls_ind, cls in enumerate(self.classes):
if cls == '__background__':
continue
dets = all_boxes[cls_ind][im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing KITTI results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3],
dets[k, 4]))
if __name__ == '__main__':
d = datasets.kitti('train')
res = d.roidb
from IPython import embed
embed()
print 'Writing KITTI results to file ' + filename
with open(filename, 'wt') as f:
# for each class
for cls_ind, cls in enumerate(self.classes):
if cls == '__background__':
continue
dets = all_boxes[cls_ind][im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(\
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
def evaluate_proposals_msr(self, all_boxes, output_dir):
# for each image
for im_ind, index in enumerate(self.image_index):
filename = os.path.join(output_dir, index + '.txt')
print 'Writing KITTI results to file ' + filename
with open(filename, 'wt') as f:
dets = all_boxes[im_ind]
if dets == []:
continue
for k in xrange(dets.shape[0]):
f.write('{:f} {:f} {:f} {:f} {:.32f}\n'.format(dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], dets[k, 4]))
if __name__ == '__main__':
d = datasets.kitti('train')
res = d.roidb
from IPython import embed; embed()
path = os.path.join(os.path.dirname(__file__), "VOCdevkit-matlab-wrapper")
cmd = "cd {} && ".format(path)
cmd += "{:s} -nodisplay -nodesktop ".format(datasets.MATLAB)
cmd += '-r "dbstop if error; '
cmd += "voc_eval('{:s}','{:s}','{:s}','{:s}',{:d}); quit;\"".format(
self._devkit_path, comp_id, self._image_set, output_dir, int(rm_results)
)
print ("Running:\n{}".format(cmd))
status = subprocess.call(cmd, shell=True)
def evaluate_detections(self, all_boxes, output_dir):
comp_id = self._write_voc_results_file(all_boxes)
# self._do_matlab_eval(comp_id, output_dir)
def competition_mode(self, on):
if on:
self.config["use_salt"] = False
self.config["cleanup"] = False
else:
self.config["use_salt"] = True
self.config["cleanup"] = True
if __name__ == "__main__":
d = datasets.kitti("trainval")
res = d.roidb
from IPython import embed
embed()
f.write('{:s} -1 -1 {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.2f} {:.3f}\n' \
.format(cls.lower(), alpha, \
dets[k, 0], dets[k, 1], dets[k, 2], dets[k, 3], \
dets3D[k, 2], dets3D[k, 3], dets3D[k, 1], \
dets3D[k, 4], dets3D[k, 5], dets3D[k, 6], dets3D[k, 0], dets[k, 4]))
return path
def _do_eval(self, path, output_dir='output'):
cmd = os.path.join(datasets.ROOT_DIR, 'kitti/eval/cpp/evaluate_object {}'.format(os.path.dirname(path)))
print('Running:\n{}'.format(cmd))
status = subprocess.call(cmd, shell=True)
def evaluate_detections(self, all_boxes, all_boxes3D, output_dir):
path = self._write_kitti_results_file(all_boxes, all_boxes3D)
if self._image_set != 'test':
self._do_eval(path)
def competition_mode(self, on):
if on:
self.config['use_salt'] = False
self.config['cleanup'] = False
else:
self.config['use_salt'] = True
self.config['cleanup'] = True
if __name__ == '__main__':
d = datasets.kitti('train', 'car')
res = d.roidb
from IPython import embed; embed()
def main():
''' Main function'''
parser = argparse.ArgumentParser(
description=
'Convert from datasets (COCO, UA-DETRAC, MOT2020, Bdd100k, AIHub, CrowdHuman, VisDrone, kitti) to YOLO format.'
)
parser.add_argument(
'--mode',
type=str,
help='type of program. e.g. parse/convert/both/analysis')
parser.add_argument(
'--datasets',
type=str,
help=
'type of datasets (COCO, DETRAC, MOT2020, Bdd100k, AIHub, CrowdHuman, VisDrone, kitti)'
)
parser.add_argument('--datasetsDir',
type=str,
help='directory of datasets')
parser.add_argument('--save', action='store_true', help='Save the file.')
parser.add_argument('--manipastFile',
type=str,
help='manipast file',
default="manipast.txt")
parser.add_argument('--copy', action='store_true', help='Copy of images')
parser.add_argument('--copyDir',
type=str,
help='directory of save target images',
default='./copy')
parser.add_argument('--negative', action='store_true', help='')
config = parser.parse_args()
config.imgNum = [0 for i in range(5)]
config.classNum = [0 for i in range(5)]
# Car, Van, Truck, Tram, Pedestrian, Cyclist
config.labelDict = {
"Van": 0,
"Car": 0,
"van": 0,
"car": 0,
"bus": 1,
"Truck": 2,
"truck": 2,
"others": 2,
"motorcycle": 3,
"motor": 3,
"motorbike": 3,
"Cyclist": 4,
"people": 4,
"person": 4,
"rider": 4,
"pedestrian": 4
}
# config.labelDict = {"Cyclist": 0, "people": 0, "person": 0, "rider": 0, "pedestrian": 0}
# config.labelDict = {"Van": 0, "Car": 0, "van": 0, "car": 0, "bus": 1, "Truck": 2, "truck": 2, "others": 2, "motorcycle": 3, "motor": 3, "motorbike":3}
if config.datasets == "detrac":
config.copy == True
commonData = None
if config.mode == 'parse' or config.mode == 'both':
if config.datasets == "coco":
model = coco(config)
elif config.datasets == "aihub":
model = aihub(config)
elif config.datasets == "bdd100k":
model = bdd100k(config)
elif config.datasets == "detrac":
model = detrac(config)
elif config.datasets == "crowdhuman":
model = crowdhuman(config)
elif config.datasets == "detrac":
model = detrac(config)
elif config.datasets == "visdrone":
model = visdrone(config)
elif config.datasets == "kitti":
model = kitti(config)
elif config.datasets == "testworks":
config.labelDict = {
"pedestrian": 0,
"vehicle": 1,
"suv": 2,
"van": 3,
"small_truck": 4,
"large_truck": 5,
"bus": 6,
"bike": 7,
"motor_cycle": 8,
"ambulance": 9,
"fire_truck": 10,
"police_car": 11,
"special_car": 12,
"wheel_chair": 13,
"wreck_car": 14,
"smart_mobility": 15
}
model = testworks(config)
commonData = model.parse()
save_commonData(commonData, config.datasets)
if config.mode == 'convert' or config.mode == 'both':
converter = Converter(config)
if commonData == None:
commonData = load_commonData(config.datasets)
converter.yolo(commonData, save=config.save, copy=config.copy)
if config.mode == 'analysis':
converter = Converter(config)
if commonData == None:
commonData = load_commonData(config.datasets)
converter.analysis(commonData)