These are chat archives for dmlc/mxnet

13th
Feb 2017
Jiajia Geng
@saicoco
Feb 13 2017 11:32
sym ==symbol
I think, there are many abbreviation for short, like mx.module==mx.mod, mx.monitor==mx.mon,mx.ndarray==mx.nd,mx.visualization==mx.vis .etc
Chih-Wei (Bert) Chang
@lazywei
Feb 13 2017 14:24
is anyone familiar with seq2seq? Is there any ready-to-use seq2seq model in MXNET?
Huiting Liu
@HuitingLiu
Feb 13 2017 14:33
Does mxnet have something like feed_previous argument for seq2seq in Tensorflow? If setting feed_previous to False. This means that the decoder will use decoder_inputs tensors as provided. If setting feed_previous to True, the decoder would only use the first element of decoder_inputs.
I have looked at several examples in MXNet. Many of them only have the training part and leave the predicting part empty because there is not real data for the decoder in the predicting process. So after training the model, users don't know how to use it.
Ashwin Jeyaseelan
@8Gitbrix
Feb 13 2017 16:29
I'm having trouble finding the number of epochs I need in my model fit method, could someone check my error?