num_boxes = num_boxes.cuda()
gt_boxes = gt_boxes.cuda()
# make variable
im_data = Variable(im_data)
im_info = Variable(im_info)
num_boxes = Variable(num_boxes)
gt_boxes = Variable(gt_boxes)
if args.cuda:
cfg.CUDA = True
# initilize the network here.
if args.net == 'detnet59':
FPN = detnet(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:
cfg.EXP_NAME = args.exp_name
if not os.path.exists(input_dir):
raise Exception('There is no input directory for loading network from ' + input_dir)
cfg.TRAIN.USE_FLIPPED = False
imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdbval_name, False)
imdb.competition_mode(on=True)
print('{:d} roidb entries'.format(len(roidb)))
load_name = os.path.join(input_dir,
'fpn_{}_{}_{}.pth'.format(args.checksession, args.checkepoch, args.checkpoint))
# initilize the network here.
if args.net == 'detnet59':
fpn = detnet(imdb.classes, 59, pretrained=False, class_agnostic=args.class_agnostic)
else:
print("network is not defined")
pdb.set_trace()
fpn.create_architecture()
print("load checkpoint %s" % (load_name))
checkpoint = torch.load(load_name)
fpn.load_state_dict(checkpoint['model'])
if 'pooling_mode' in checkpoint.keys():
cfg.POOLING_MODE = checkpoint['pooling_mode']
print('load model successfully!')
im_data = torch.FloatTensor(1)
im_info = torch.FloatTensor(1)
