sonack

@thangduong I agree with you. I found the mask and padding is only applied on the embedding layer, while the subsequent conv layers are not. I guess it may cause...

> @ruotianluo Zero padding is used in every layer to keep the layer size same: https://github.com/anantzoid/Language-Modeling-GatedCNN/blob/master/model.py#L62 > The zero padding I referred to in the above comment is the extra...

@qixiang109 Are you working on this gated cnn？do you have successfully reproduce the paper’s result？I hope we can communicate with each other ：)

Me too, have you found any solution? @Jar7

@Cynicsss How did you control the BN sync or not sync? I found the bn in resnet is original all sync already? What do you mean by `,but when the...

> > @Cynicsss How did you control the BN sync or not sync? I found the bn in resnet is original all sync already? What do you mean by `,but...

did you used the syncd bn option？

@QQ1696311291 你的数据应该没放对位置

I found the fix solution! Change the Line 61 of `src/models/sequence_predictor_model.py` `cell = tf.nn.rnn_cell.MultiRNNCell([cell] * self.config.num_layers, state_is_tuple=False)` to ``` def new_cell(): if self.config.model_type == "gru": cell = tf.nn.rnn_cell.GRUCell(self.config.hidden_size) elif self.config.model_type...

How did you use gzip to compress files? Did you compress directly on the generated `.txt` text files? I am wondering how much the encoding schema will affect the final...