Gokce Keskin

Potential Issue with EncoderDecoder Model with CrossEntropy Loss

2

Hi, I see that the LSTM Attention Decoder takes the log_softmax of the step outputs [inside the model](https://github.com/openspeech-team/openspeech/blob/main/openspeech/decoders/lstm_attention_decoder.py#L155). However, cross entropy loss uses [nn.CrossEntropyLoss](https://github.com/openspeech-team/openspeech/blob/main/openspeech/criterion/cross_entropy/cross_entropy.py#L108), which takes another log_softmax inside. Shouldn't...

Hi, Thanks a lot for your example of char_rnn. I have a question about your usage of unchain_backward (line 107) in the train.py. Assume batchsize is 1, and the code...

Embedding Layer + SGRU

7

Hi, I am trying to use the SGRU, but running into an issue while using it with an embedding layer. I have sequences of length "maxlen", and each element of...