zheng-da commented on a change in pull request #9977: Cpu lstm inference URL: https://github.com/apache/incubator-mxnet/pull/9977#discussion_r172710204
########## File path: src/operator/rnn-inl.h ########## @@ -78,10 +82,12 @@ inline int rnn_param_size(int layerNum, int size = rnn_single_param_size(inputSize, hiddenSize, mode); // get size of remaining layers if (bidirectional) { - size += (layerNum - 1) * rnn_single_param_size(2 * hiddenSize, hiddenSize, mode); + size += (layerNum - 1) * rnn_single_param_size(2 * hiddenSize, + hiddenSize, mode); size *= 2; } else { - size += (layerNum - 1) * rnn_single_param_size(hiddenSize, hiddenSize, mode); + size += (layerNum - 1) * rnn_single_param_size(hiddenSize, hiddenSize, + mode); Review comment: you are just reformatting the code here? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services