TypeError: lstm() received an invalid combination of arguments

TypeError: lstm() received an invalid combination of arguments - got (Tensor, tuple, list, bool, int, float, bool, int, bool), but expected one of:
 * (Tensor data, Tensor batch_sizes, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional)
      didn't match because some of the arguments have invalid types: (Tensor, !tuple!, !list!, !bool!, !int!, !float!, !bool!, !int!, bool)
 * (Tensor input, tuple of Tensors hx, tuple of Tensors params, bool has_biases, int num_layers, float dropout, bool train, bool bidirectional, bool batch_first)
      didn't match because some of the arguments have invalid types: (Tensor, !tuple!, !list!, bool, int, float, bool, !int!, bool)

lstm更新到高版本之后，bidirectional参数不能使用int类型（0或1），要使用bool类型（False或True），要不会报上述错误。

问题解决参考自：Error with LSTM when switching from 0.4 to 1.0 (invalid combination of arguments) - nlp - PyTorch Forums