模型选择的是Adam优化器。以下是报错信息以及部分代码。我寻思我也没往优化器离传入int类型的数据啊？？咋回事这是？头一次遇见。求大佬指点

Traceback (most recent call last):
  File "/home/harry/Python_Demo/Paddlebased/SLBR_motif_removal/train.py", line 191, in 
    main()
  File "/home/harry/Python_Demo/Paddlebased/SLBR_motif_removal/train.py", line 186, in main
    model.train()
  File "/home/harry/Python_Demo/Paddlebased/SLBR_motif_removal/train.py", line 104, in train
    self.train_one_epoch(epoch)
  File "/home/harry/Python_Demo/Paddlebased/SLBR_motif_removal/train.py", line 76, in train_one_epoch
    self.optimizer.step()
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/paddle/fluid/dygraph/base.py", line 299, in __impl__
    return func(*args, **kwargs)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/decorator.py", line 232, in fun
    return caller(func, *(extras + args), **kw)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/paddle/fluid/wrapped_decorator.py", line 25, in __impl__
    return wrapped_func(*args, **kwargs)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/paddle/fluid/framework.py", line 434, in __impl__
    return func(*args, **kwargs)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/paddle/optimizer/adam.py", line 451, in step
    loss=None, startup_program=None, params_grads=params_grads)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/paddle/optimizer/optimizer.py", line 954, in _apply_optimize
    params_grads, self.regularization)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/paddle/optimizer/optimizer.py", line 1039, in append_regularization_ops
    regularization)
  File "/home/harry/.conda/envs/Paddle/lib/python3.7/site-packages/paddle/optimizer/optimizer.py", line 986, in _create_regularization_of_grad
    regularization_term = regularization(param, grad, grad.block)
TypeError: 'int' object is not callable

Process finished with exit code 1

    def __init__(self, args):
        # 加载参数
        self.args = args

        # 模型加载
        print("==> 创建模型 ")
        self.model = SLBR(args=self.args)
        print("==> 成功创建模型")

        # 学习率与优化器
        self.scheduler = paddle.optimizer.lr.StepDecay(learning_rate=self.args.lr, step_size=self.args.schedule,
                                                  gamma=self.args.gamma)
        # self.scheduler = 1e-3  # 创建一个随着epoch变化的学习率
        self.optimizer = paddle.optimizer.Adam(parameters=self.model.parameters(),
                                          learning_rate=self.scheduler, beta1=self.args.beta1, beta2=self.args.beta2,
                                          weight_decay=self.args.weight_decay)
        # self.lr = self.args.lr

        # 数据集加载
        train_sets = DEHW(root=self.args.train_sets, train=True)
        self.len_train_sets = len(train_sets)
        self.train_loader = DataLoader(train_sets, batch_size=self.args.batch_size, num_workers=self.args.num_workers)
        val_sets = DEHW(root=self.args.val_sets, train=False)
        self.len_val_sets = len(val_sets)
        self.val_loader = DataLoader(val_sets, batch_size=1, num_workers=2)

        # 日志的主目录checkpoint，不存在则创建
        check_dir(os.path.join(self.args.checkpoint))
        # 创建tensorboard
        self.tensorboard = Tensorboard(mode="paddle", logdir=self.args.tensorboard_path)

        # 一些指标的记录
        self.best_acc = 0
        self.is_best = False
        self.current_epoch = 0
        self.metric = -100000
        self.hl = 6 if self.args.hl else 1
        self.step = 0


        # 损失函数
        self.loss = Losses(self.args)

        # 指标计算
        self.metric = Metrics()

        print('==> 总参数量: %.2fM' % (sum(p.numel() for p in self.model.parameters()) / 1e6))
        print('==> 当前存储目录: %s' % (self.args.checkpoint))

    def train_one_epoch(self, epoch):
        self.model.train()
        current_batch = 0
        for i, (inputs, gts, masks) in enumerate(self.train_loader):
            self.optimizer.clear_grad()
            current_batch += self.args.batch_size
            outputs = self.model(inputs)
            coarse_loss, refine_loss, style_loss, mask_loss = self.loss(
                 outputs[0], gts, outputs[1], masks)
            total_loss = self.args.lambda_l1 * (coarse_loss + refine_loss) + self.args.lambda_mask * (
                mask_loss) + style_loss
            total_loss.backward()
            self.optimizer.step() # 这一步报错