asappresearch / sru

Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
MIT License
2.11k stars 306 forks source link

A little question about the architecture #44

Closed Mendel1 closed 6 years ago

Mendel1 commented 6 years ago

Could anyone tell me some tips about the architechture? 2 In the last equation, does that mean input x_t should have the same size as output h_t ?As it is element-wise product...... Thanks a lot.

taoleicn commented 6 years ago

See the answer here: https://github.com/taolei87/sru/issues/12

Mendel1 commented 6 years ago

Got it.Thank you very much