# 'sheep', 'sofa', 'train', 'tvmonitor'])
classes = np.asarray(['__background__', 'diabete'])
if args.cascade:
if args.net == 'detnet59':
fpn = detnet_cascade(classes,
59,
pretrained=False,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
else:
if args.net == 'detnet59':
fpn = detnet_noncascade(classes,
59,
pretrained=False,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
fpn.create_architecture()
# checkpoint = torch.load(load_name)
# fpn.load_state_dict(checkpoint['model'])
checkpoint = torch.load(load_name)
fpn.load_state_dict({
k: v
for k, v in checkpoint['model'].items() if k in fpn.state_dict()
})
cfg.CUDA = True
# initilize the network here.
if args.cascade:
if args.net == 'detnet59':
FPN = detnet_cascade(imdb.classes,
59,
pretrained=True,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
else:
if args.net == 'detnet59':
FPN = detnet_noncascade(imdb.classes,
59,
pretrained=True,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
FPN.create_architecture()
lr = cfg.TRAIN.LEARNING_RATE
lr = args.lr
# tr_momentum = cfg.TRAIN.MOMENTUM
# tr_momentum = args.momentum
params = []
for key, value in dict(FPN.named_parameters()).items():
if value.requires_grad:
