101,
pretrained=pretrained,
class_agnostic=args.class_agnostic,
imagenet_weight=args.imagenet_weight)
elif args.net == 'mobilenet_v2':
fasterRCNN = mobilenet(imdb.classes,
'v2',
pretrained=pretrained,
class_agnostic=args.class_agnostic,
imagenet_weight=args.imagenet_weight)
elif args.net == 'shufflenet_x05':
fasterRCNN = shufflenet(imdb.classes,
'x05',
pretrained=pretrained,
class_agnostic=args.class_agnostic,
imagenet_weight=args.imagenet_weight)
elif args.net == 'shufflenet_x10':
fasterRCNN = shufflenet(imdb.classes,
'x10',
pretrained=pretrained,
class_agnostic=args.class_agnostic,
imagenet_weight=args.imagenet_weight)
elif args.net == 'squeezenet_10':
fasterRCNN = squeezenet(imdb.classes,
'10',
pretrained=pretrained,
class_agnostic=args.class_agnostic,
imagenet_weight=args.imagenet_weight)
fasterRCNN = resnet(pascal_classes,
50,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'res152':
fasterRCNN = resnet(pascal_classes,
152,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'mobilenet':
fasterRCNN = mobilenet(pascal_classes,
pretrained=False,
class_agnostic=args.class_agnostic)
elif args.net == 'shufflenet':
fasterRCNN = shufflenet(pascal_classes,
pretrained=False,
class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
fasterRCNN.create_architecture()
print("load checkpoint %s" % (load_name))
if args.cuda > 0:
checkpoint = torch.load(load_name)
else:
checkpoint = torch.load(load_name,
map_location=(lambda storage, loc: storage))
fasterRCNN.load_state_dict(checkpoint['model'])
if 'pooling_mode' in checkpoint.keys():