閱讀論文 《Train RNN as fast as CNN》

Train RNN as fast as CNN @(NLP)[cuDNN-LSTM, SRU] ABSTRACT 作者提出了一個簡單循環單元的架構(SRU),能夠輕易的實現並行化。SRU像CNN一樣快,比優化後的LSTM實現快5到10倍。 In SRU, the majority of computation for each step is independent of the recurre
相關文章
相關標籤/搜索