mindspore情感分析时RNN网络搭建出错

在参考https://gitee.com/mindspore/docs/blob/r1.1/tutorials/training/source_zh_cn/advanced_use/nlp_sentimentnet.md#%E4%BD%BF%E7%94%A8sentimentnet%E5%AE%9E%E7%8E%B0%E6%83%85%E6%84%9F%E5%88%86%E7%B1%BB进行情感分类实战训练时，想要把lstm网络改为rnn网络

【操作步骤&问题现象】

在查看mindsprore文档后发现nn.RNN和nn.LSTM的区别在于LSTM比RNN多一个参数c，把代码中的所有c删除后训练时出现函数参数个数不匹配的原因，但本人水平有限，没有找到具体哪里导致的这个原因。

【截图信息】

修改后代码如下：

# 定义需要单层LSTM小算子堆叠的设备类型。
STACK_LSTM_DEVICE = ["CPU"]
# 短期内存（h）和长期内存（c）初始化为0
# 定义lstm_default_state函数来初始化网络参数及网络状态。
def lstm_default_state(batch_size, hidden_size, num_layers, bidirectional):
    """初始化默认输入."""
    num_directions = 2 if bidirectional else 1
    h = Tensor(np.zeros((num_layers * num_directions, batch_size, hidden_size)).astype(np.float32))
    #c = Tensor(np.zeros((num_layers * num_directions, batch_size, hidden_size)).astype(np.float32))
    return h

def stack_lstm_default_state(batch_size, hidden_size, num_layers, bidirectional):
    """init default input."""
    num_directions = 2 if bidirectional else 1

    h_list =  []
    for _ in range(num_layers):
        h_list.append(Tensor(np.zeros((num_directions, batch_size, hidden_size)).astype(np.float32)))
        #c_list.append(Tensor(np.zeros((num_directions, batch_size, hidden_size)).astype(np.float32)))
    h= tuple(h_list)
    return h

# 针对不同的场景，自定义单层LSTM小算子堆叠，来实现多层LSTM大算子功能。
class StackRNN(nn.Cell):
    """
    Stack multi-layers LSTM together.
    """

    def __init__(self,
                 input_size,
                 hidden_size,
                 num_layers=3,
                 has_bias=True,
                 batch_first=False,
                 dropout=0.0,
                 bidirectional=True):
        super(StackRNN, self).__init__()
        self.num_layers = num_layers
        self.batch_first = batch_first
        self.transpose = ops.Transpose()

        # direction number
        num_directions = 2 if bidirectional else 1

        # input_size list
        input_size_list = [input_size]
        for i in range(num_layers - 1):
            input_size_list.append(hidden_size * num_directions)

        # layers
        layers = []
        for i in range(num_layers):
            layers.append(nn.RNNCell(input_size=input_size_list[i],
                                      hidden_size=hidden_size,
                                      has_bias=has_bias,
                                      
                                     
                                      ))

        # weights
        weights = []
        for i in range(num_layers):
            # weight size
            weight_size = (input_size_list[i] + hidden_size) * num_directions * hidden_size * 4
            if has_bias:
                bias_size = num_directions * hidden_size * 4
                weight_size = weight_size + bias_size

            # numpy weight
            stdv = 1 / math.sqrt(hidden_size)
            w_np = np.random.uniform(-stdv, stdv, (weight_size, 1, 1)).astype(np.float32)

            # lstm weight
            weights.append(Parameter(initializer(Tensor(w_np), w_np.shape), name="weight" + str(i)))

        # 
        self.lstms = layers
        self.weight = ParameterTuple(tuple(weights))
        print(1)
        
    def construct(self, x, hx):
        """construct"""
        print(2)
        if self.batch_first:
            x = self.transpose(x, (1, 0, 2))
        # stack lstm
        h= hx
        hn= None
        for i in range(self.num_layers):
            x, hn,  _, _ = self.lstms[i](x, h[i], self.weight[i])
        if self.batch_first:
            x = self.transpose(x, (1, 0,2))
        
        return x, (hn)

其他部分未作修改

【日志信息】（可选，上传日志内容或者附件）

从报错信息来看是因为你的函数要求参数是两个但实际提供了三个，那么应该是你有地方删除c变量时没有删除干净，若是寻找比较难你可以开启pynative模式，https://www.mindspore.cn/tutorials/zh-CN/r1.7/advanced/pynative_graph/pynative.html?highlight=pynative， 参考该文档寻找哪一块没有配置好。