if bbox_in_expand_region(gt_bbox, all_expand_boxes[idx]):
nrecall += 1
print("expand region recall")
print("{}/{}: {:.4f}".format(nrecall, npos, nrecall/npos))
def evaluate_detections(box_list, output_dir, dataset):
write_voc_results_file(box_list, dataset)
do_python_eval(output_dir)
if __name__ == '__main__':
# load net
net = build_ssd('test', args.input_size, args.input_size_2, 2, args.expand_num) # initialize SSD
net.load_state_dict(torch.load(args.trained_model))
net.eval()
print('Finished loading model!')
# load data
dataset = CAR_CARPLATEDetection(root=args.voc_root,
transform=BaseTransform(args.input_size, dataset_mean),
target_transform=CAR_CARPLATEAnnotationTransform(keep_difficult=True),
dataset_name=set_type)
if args.cuda:
net = net.cuda()
cudnn.benchmark = True
# evaluation
test_net(args.save_folder, net, args.cuda, dataset,
BaseTransform(net.size, dataset_mean), args.top_k, args.input_size,
thresh=args.confidence_threshold)
default='weights/voc_weights/VOC300.pth', type=str,
help='Trained state_dict file path to open')
parser.add_argument('--obj_type', default='car_carplate', choices=['car_carplate', 'car', 'carplate'],
type=str, help='car or carplate')
args = parser.parse_args()
if args.obj_type in ['car', 'carplate']:
net = build_ssd('test', args.input_size, 2) # initialize SSD
elif args.obj_type == 'car_carplate':
net = build_ssd('test', args.input_size, 3)
net.load_weights(args.trained_model)
# matplotlib inline
from matplotlib import pyplot as plt
from data import CAR_CARPLATEDetection, CAR_CARPLATEAnnotationTransform, CAR_CARPLATE_ROOT
testset = CAR_CARPLATEDetection(CAR_CARPLATE_ROOT, None, None, CAR_CARPLATEAnnotationTransform(),
dataset_name='test')
for img_id in range(100):
image = testset.pull_image(img_id)
rgb_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
x = cv2.resize(image, (args.input_size, args.input_size)).astype(np.float32)
x -= (104.0, 117.0, 123.0)
x = x.astype(np.float32)
x = x[:, :, ::-1].copy()
x = torch.from_numpy(x).permute(2, 0, 1)
xx = Variable(x.unsqueeze(0)) # wrap tensor in Variable
if torch.cuda.is_available():
xx = xx.cuda()
y = net(xx)