Closed zxy951005 closed 5 years ago
In default, it will use gpu when the system detects the gpu.
https://github.com/jiesutd/LatticeLSTM/blob/3f960348ea07b065afff653949046f09470332f4/main.py#L395
没用上batch所以速度好慢啊,训练一天才8个epoch > _ < 。谢谢作者,回复好快。
I am a little bit confused why can't it use batch during training..?
I am a little bit confused why can't it use batch during training..?
Because it is hard to implement the real batched lattice LSTM, as each input has a different shortcut link. The batched version is possible, but it is a little complicated.
does the batched version meaning we should padding inner padding?
gpu=True,但是也没用GPU, 哪儿需要改动,model后面加个cuda()就完了吗?还是还有其他也要改。