def __init__(self,
trained_model,
network="mobile0.25",
cpu=False,
origin_size=True,
confidence_threshold=0.02,
nms_threshold=0.4):
torch.set_grad_enabled(False)
self.origin_size = origin_size
self.confidence_threshold = confidence_threshold
self.nms_threshold = nms_threshold
self.cfg = None
if network == "mobile0.25":
self.cfg = cfg_mnet
elif network == "resnet50":
self.cfg = cfg_re50
# net and model
self.net = RetinaFace(cfg=self.cfg, phase='test')
self.net = self.load_model(self.net, trained_model, cpu)
self.net.eval()
print('Finished loading model!')
print(self.net)
cudnn.benchmark = True
self.device = torch.device("cpu" if cpu else "cuda")
self.net = self.net.to(self.device)
self._t = {'forward_pass': Timer(), 'misc': Timer()}
pretrained_dict = remove_prefix(pretrained_dict, 'module.')
check_keys(model, pretrained_dict)
model.load_state_dict(pretrained_dict, strict=False)
return model
if __name__ == '__main__':
torch.set_grad_enabled(False)
cfg = None
if args.network == "mobile0.25":
cfg = cfg_mnet
elif args.network == "resnet50":
cfg = cfg_re50
# net and model
net = RetinaFace(cfg=cfg, phase='test')
net = load_model(net, args.trained_model, args.cpu)
net.eval()
print('Finished loading model!')
print(net)
cudnn.benchmark = True
device = torch.device("cpu" if args.cpu else "cuda")
net = net.to(device)
# testing dataset
testset_folder = args.dataset_folder
testset_list = args.dataset_folder[:-7] + "wider_val.txt"
with open(testset_list, 'r') as fr:
test_dataset = fr.read().split()
num_images = len(test_dataset)
num_classes = 2
img_dim = cfg['image_size']
num_gpu = cfg['ngpu']
batch_size = cfg['batch_size']
max_epoch = cfg['epoch']
gpu_train = cfg['gpu_train']
num_workers = args.num_workers
momentum = args.momentum
weight_decay = args.weight_decay
initial_lr = args.lr
gamma = args.gamma
training_dataset = args.training_dataset
save_folder = args.save_folder
net = RetinaFace(cfg=cfg)
print("Printing net...")
print(net)
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]
if head == 'module.':
name = k[7:] # remove `module.`
else:
name = k
class RetinaFaceNet:
def __init__(self,
trained_model,
network="mobile0.25",
cpu=False,
origin_size=True,
confidence_threshold=0.02,
nms_threshold=0.4):
torch.set_grad_enabled(False)
self.origin_size = origin_size
self.confidence_threshold = confidence_threshold
self.nms_threshold = nms_threshold
self.cfg = None
if network == "mobile0.25":
self.cfg = cfg_mnet
elif network == "resnet50":
self.cfg = cfg_re50
# net and model
self.net = RetinaFace(cfg=self.cfg, phase='test')
self.net = self.load_model(self.net, trained_model, cpu)
self.net.eval()
print('Finished loading model!')
print(self.net)
cudnn.benchmark = True
self.device = torch.device("cpu" if cpu else "cuda")
self.net = self.net.to(self.device)
self._t = {'forward_pass': Timer(), 'misc': Timer()}
# testing begin
def check_keys(self, model, pretrained_state_dict):
ckpt_keys = set(pretrained_state_dict.keys())
model_keys = set(model.state_dict().keys())
used_pretrained_keys = model_keys & ckpt_keys
unused_pretrained_keys = ckpt_keys - model_keys
missing_keys = model_keys - ckpt_keys
print('Missing keys:{}'.format(len(missing_keys)))
print('Unused checkpoint keys:{}'.format(len(unused_pretrained_keys)))
print('Used keys:{}'.format(len(used_pretrained_keys)))
assert len(
used_pretrained_keys) > 0, 'load NONE from pretrained checkpoint'
return True
def remove_prefix(self, state_dict, prefix):
''' Old style model is stored with all names of parameters sharing common prefix 'module.' '''
print('remove prefix \'{}\''.format(prefix))
f = lambda x: x.split(prefix, 1)[-1] if x.startswith(prefix) else x
return {f(key): value for key, value in state_dict.items()}
def load_model(self, model, pretrained_path, load_to_cpu):
print('Loading pretrained model from {}'.format(pretrained_path))
if load_to_cpu:
pretrained_dict = torch.load(
pretrained_path, map_location=lambda storage, loc: storage)
else:
device = torch.cuda.current_device()
pretrained_dict = torch.load(
pretrained_path,
map_location=lambda storage, loc: storage.cuda(device))
if "state_dict" in pretrained_dict.keys():
pretrained_dict = self.remove_prefix(pretrained_dict['state_dict'],
'module.')
else:
pretrained_dict = self.remove_prefix(pretrained_dict, 'module.')
self.check_keys(model, pretrained_dict)
model.load_state_dict(pretrained_dict, strict=False)
return model
def detect(self, img, *_):
# testing scale
img = img.astype(np.float32)
target_size = 1600
max_size = 2150
im_shape = img.shape
im_size_min = np.min(im_shape[0:2])
im_size_max = np.max(im_shape[0:2])
resize = float(target_size) / float(im_size_min)
# prevent bigger axis from being more than max_size:
if np.round(resize * im_size_max) > max_size:
resize = float(max_size) / float(im_size_max)
if self.origin_size:
resize = 1
if resize != 1:
img = cv2.resize(img,
None,
None,
fx=resize,
fy=resize,
interpolation=cv2.INTER_LINEAR)
im_height, im_width, _ = img.shape
scale = torch.Tensor(
[img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
img -= (104, 117, 123)
img = img.transpose(2, 0, 1)
img = torch.from_numpy(img).unsqueeze(0)
img = img.to(self.device)
scale = scale.to(self.device)
self._t['forward_pass'].tic()
loc, conf, landms = self.net(img) # forward pass
self._t['forward_pass'].toc()
self._t['misc'].tic()
priorbox = PriorBox(self.cfg, image_size=(im_height, im_width))
priors = priorbox.forward()
priors = priors.to(self.device)
prior_data = priors.data
boxes = decode(loc.data.squeeze(0), prior_data, self.cfg['variance'])
boxes = boxes * scale / resize
boxes = boxes.cpu().numpy()
scores = conf.squeeze(0).data.cpu().numpy()[:, 1]
landms = decode_landm(landms.data.squeeze(0), prior_data,
self.cfg['variance'])
scale1 = torch.Tensor([
img.shape[3], img.shape[2], img.shape[3], img.shape[2],
img.shape[3], img.shape[2], img.shape[3], img.shape[2],
img.shape[3], img.shape[2]
])
scale1 = scale1.to(self.device)
landms = landms * scale1 / resize
landms = landms.cpu().numpy()
# ignore low scores
inds = np.where(scores > self.confidence_threshold)[0]
boxes = boxes[inds]
landms = landms[inds]
scores = scores[inds]
# keep top-K before NMS
order = scores.argsort()[::-1]
# order = scores.argsort()[::-1][:args.top_k]
boxes = boxes[order]
landms = landms[order]
scores = scores[order]
# do NMS
dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32,
copy=False)
keep = py_cpu_nms(dets, self.nms_threshold)
# keep = nms(dets, args.nms_threshold,force_cpu=args.cpu)
dets = dets[keep, :]
landms = landms[keep]
# keep top-K faster NMS
# dets = dets[:args.keep_top_k, :]
# landms = landms[:args.keep_top_k, :]
#dets = np.concatenate((dets, landms), axis=1)
self._t['misc'].toc()
return dets