f.write('{:s}\n'.format(event[0][0] + '/' + im_name + '.jpg'))
f.write('{:d}\n'.format(det.shape[0]))
for i in range(det.shape[0]):
xmin = det[i][0]
ymin = det[i][1]
xmax = det[i][2]
ymax = det[i][3]
score = det[i][4]
f.write('{:.1f} {:.1f} {:.1f} {:.1f} {:.3f}\n'.format(
xmin, ymin, (xmax - xmin + 1), (ymax - ymin + 1), score))
if __name__ == '__main__':
# net and model
if args.net == "mv2":
net = S3FD_MV2(phase='test', size=None,
num_classes=2) # initialize detector
elif args.net == "FairNAS_A":
net = S3FD_FairNAS_A(phase='test', size=None, num_classes=2)
elif args.net == "FairNAS_B":
net = S3FD_FairNAS_B(phase='test', size=None, num_classes=2)
net = load_model(net, args.trained_model)
net.eval()
print('Finished loading model!')
print(net)
print(args.cuda)
if args.cuda:
net = net.cuda()
cudnn.benchmark = True
else:
net = net.cpu()
"""Detect object classes in an image using pre-computed object proposals."""
sys.stdout = Logger(os.path.join(args.save_folder, 'log.txt'))
# TensorBoardX
summary = TensorboardSummary(args.save_folder)
writer = summary.create_summary()
img_dim = 640
rgb_means = (104, 117, 123)
num_classes = 2
batch_size = args.batch_size
weight_decay = args.weight_decay
gamma = args.gamma
momentum = args.momentum
if args.net == 'vgg16':
net = S3FD('train', img_dim, num_classes)
elif args.net == 'mv2':
net = S3FD_MV2('train', img_dim, num_classes)
print("Printing net...")
print(net)
'''if os.path.isfile(args.pretrained):
vgg_weights = torch.load(args.pretrained)
print('Loading VGG network...')
net.vgg.load_state_dict(vgg_weights)'''
if args.resume_net is not None:
print('Loading resume network...')
state_dict = torch.load(args.resume_net)
# create new OrderedDict that does not contain `module.`
from collections import OrderedDict
new_state_dict = OrderedDict()
for k, v in state_dict.items():
head = k[:7]