gru单元出错

[LuciferTian]

运行到score, _ = model(x)时，出错，不知道是什么原因呢？TypeError: gru() received an invalid combination of arguments - got (Tensor, Tensor, list, float, int, float, bool, bool, bool), but expected one of:

• (Tensor data, Tensor batch_sizes, Tensor 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, Tensor, list, float, int, float, bool, bool, bool)
• (Tensor input, Tensor 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, Tensor, list, float, int, float, bool, bool, bool)

[ArnoldIOI]

Same error!

[lushunn]

self.rnn = nn.GRU(embed_dim, hidden_size, num_layers, dropout) ，把droupout去掉就行了。

[zl535320706]

can refer https://github.com/xiadingZ/video-caption.pytorch/issues/32

[Lily-code111]

self.rnn = nn.GRU(embed_dim, hidden_size, num_layers, dropout) ，把droupout去掉就行了。

why?

[William20234]

Could you provide some trained models in order that we don't need to train them ourselves?

[windsmileknight]

Define the 'dropout' as keyword argments could solve this issue, such as, self.gru = torch.GRU(xxx, xxx, xxx, dropout=dropout).