# print(left_up)
j += 1
cv2.rectangle(img, left_up, right_bottom, (0, 0, 255), 2)
conf = "{:.3f}".format(score)
point = (int(left_up[0]), int(left_up[1] - 5))
cv2.putText(img, conf, point, cv2.FONT_HERSHEY_COMPLEX, 0.6,
(0, 255, 0), 1)
t2 = time.time()
print('detect:{} timer:{}'.format(img_path, t2 - t1))
cv2.imwrite(os.path.join(args.save_dir, os.path.basename(img_path)), img)
if __name__ == '__main__':
net = build_s3fd('test', cfg.NUM_CLASSES)
net.load_state_dict(torch.load(args.model))
net.eval()
if use_cuda:
net.cuda()
# cudnn.benckmark = True
img_path = './img'
# img_path = '/home/lijc08/datasets/widerface/WIDER_val/images/0--Parade'
# img_path = './tools/eval_tools/s3fd_val/hard'
img_list = [
os.path.join(img_path, x) for x in os.listdir(img_path)
if x.endswith('jpg')
]
for path in img_list:
from data.config import cfg
from s3fd import build_s3fd
from utils.augmentations import S3FDBasicTransform
parser = argparse.ArgumentParser(description='s3df evaluatuon fddb')
parser.add_argument('--trained_model',
type=str,
default='weights/s3fd.pth',
help='trained model')
parser.add_argument('--thresh',
default=0.1,
type=float,
help='Final confidence threshold')
args = parser.parse_args()
use_cuda = torch.cuda.is_available()
if use_cuda:
torch.set_default_tensor_type('torch.cuda.FloatTensor')
else:
torch.set_default_tensor_type('torch.FloatTensor')
net = build_s3fd('train', cfg.INPUT_SIZE, cfg.NUM_CLASSES)
net.load_state_dict(torch.load(args.trained_model))
net.eval()
def dyna_anchor(imh, imw):
pass
num_workers=args.num_workers,
shuffle=True,
collate_fn=detection_collate,
pin_memory=True)
val_batchsize = args.batch_size // 2
val_loader = data.DataLoader(val_dataset,
val_batchsize,
num_workers=args.num_workers,
shuffle=False,
collate_fn=detection_collate,
pin_memory=True)
min_loss = np.inf
start_epoch = 0
s3fd_net = build_s3fd('train', cfg.HAND.NUM_CLASSES)
net = s3fd_net
if args.resume:
print('Resuming training, loading {}...'.format(args.resume))
start_epoch = net.load_weights(args.resume)
else:
vgg_weights = torch.load(args.save_folder + args.basenet)
print('Load base network....')
net.vgg.load_state_dict(vgg_weights)
if args.cuda:
if args.multigpu:
net = torch.nn.DataParallel(s3fd_net)
net = net.cuda()
def eval_wider(model_name):
event_list, file_list, imgs_path, save_path = get_data()
cfg.USE_NMS = True
net = build_s3fd('test', cfg.NUM_CLASSES)
net.load_state_dict(torch.load(model_name))
net.eval()
if use_cuda:
net.cuda()
cudnn.benckmark = True
# transform = S3FDBasicTransform(cfg.INPUT_SIZE, cfg.MEANS)
counter = 0
for index, event in enumerate(tqdm(event_list)):
filelist = file_list[index][0]
path = os.path.join(save_path, event[0][0].encode('utf-8'))
if not os.path.exists(path):
os.makedirs(path)
for num, file in enumerate(filelist):
im_name = file[0][0].encode('utf-8')
in_file = os.path.join(imgs_path, event[0][0], im_name[:] + '.jpg')
# img = cv2.imread(in_file)
img = Image.open(in_file)
if img.mode == 'L':
img = img.convert('RGB')
img = np.array(img)
# max_im_shrink = (0x7fffffff / 577.0 /
# (img.shape[0] * img.shape[1])) ** 0.5
max_im_shrink = np.sqrt(
1700 * 1200 / (img.shape[0] * img.shape[1]))
shrink = max_im_shrink if max_im_shrink < 1 else 1
counter += 1
t1 = time.time()
det0 = detect_face(net, img, shrink)
det1 = flip_test(net, img, shrink) # flip test
[det2, det3] = multi_scale_test(net, img, max_im_shrink)
det = np.row_stack((det0, det1, det2, det3))
dets = bbox_vote(det)
t2 = time.time()
#print('Detect %04d th image costs %.4f' % (counter, t2 - t1))
fout = open(osp.join(save_path, event[0][0].encode('utf-8'), im_name + '.txt'), 'w')
fout.write('{:s}\n'.format(event[0][0].encode('utf-8') + '/' + im_name + '.jpg'))
fout.write('{:d}\n'.format(dets.shape[0]))
for i in xrange(dets.shape[0]):
xmin = dets[i][0]
ymin = dets[i][1]
xmax = dets[i][2]
ymax = dets[i][3]
score = dets[i][4]
fout.write('{:.1f} {:.1f} {:.1f} {:.1f} {:.3f}\n'
.format(xmin, ymin, (xmax - xmin + 1), (ymax - ymin + 1), score))
