-
I'm attempting to recreate this [model](https://github.com/bplank/bilstm-aux) in TensorFlow but I can not seem to get anywhere close to the speed of the original code. On average the TensorFlow implem…
-
Hi. I am a newbie on TensorFlow, just like most of the others here.
I was trying to use the LSTM modules, and some questions arose.
1. How can I cope with non-fixed length of sequences? For example, t…
-
I have read the code, I can see that the controller weights are updated by RMSProp, but **where is the memOp weights updated**?? I can see that the gradients of parameters are computed, but they have …
-
This is really not an issue, so please feel free to close it and I will try asking the questions in Google Groups or Stackoverflow
I have been playing with LSTM for multi variate time series, it is …
-
In https://github.com/karpathy/char-rnn/blob/master/train.lua#L288, we have
```
-- transfer final state to initial state (BPTT)
init_state_global = rnn_state[#rnn_state] -- NOTE: I don't think this n…
-
When I see the code of Example, I don't understand that why output and target not in the same dimension on the loss function ?
-
I want to recognize the online handwriten charaters with your lstm, is there any example? The example in https://github.com/nicholas-leonard/dp/blob/master/examples/recurrentlanguagemodel.lua is langu…
-
Hi, I have a question.
Can anybody tell me whole option values of the paper's experiment setting?
Paper represents that options used in experiment like below.
#
alpha: 0.95
BPTT steps: 50(SCRNN) /…
-
Hi, I have a question about training a LSTM with multiple time series. Could you tell me how does the BPTT work at this case? Suppose these sequences are related to each other, so I can't train each s…
-
Hi,
Recent changes to the Sequencer remember/forget mechanism introduced modes like "both" and "eval", which is very convenient. However, in "eval" mode, a forward step during evaluation will set the…