-
I'm trying to translate LSTM [PennTreeBank example](https://github.com/Microsoft/CNTK/blob/master/Examples/Text/PennTreebank/Config/rnn.cntk) from SimpleNetworkBuilder to BrainScript.
I've been worki…
-
Hi,
We successfully implement a seq2seq model with auto-batching (in GPU) and it works great. We wanted to improve the speed by reducing the size of the softmax:
> Expression W = select_rows(p2c…
-
Hi, I have tried to train TE model with experiment_config/decomposable_attention.json, and I adjust the epoch number to 3000. but I have only got the best validation accuracy of 72.8%，with training ac…
-
I get the following when trying to train a model (on a CPU) after upgrading to 1.0.8. Interestingly it works if I downgrade to 1.0.7. Perhaps even more surprising is that it works (with 1.0.8) on a ub…
-
I can't run the Sequence to Sequence example. Whenever I try to run it I get this:
```
`CNTKCommandTrainBegin: train
[CALL STACK]
[0x5a0acc]
[0x5d73a1] bool Microsoft::MSR::CNTK::ConfigPar…
-
Hey guys,
I was wondering how are the initial internal states in a recurrent layer dealt with? So far it appears they are reset are every run. Is there any way to preserve them?
I'd like to be able …
-
Hey TF,
Its very nice that you support so many complex number calculations like `tf.complex_abs` and `fft`. I am trying replicate this [Associative LSTM paper ](http://arxiv.org/abs/1602.03032)where …