-
I was looking at the TF implementation and it seems that you use the same weights for the input x^{[t]} as well as the hidden state s^{[t]} in the function linear(...), but in the paper, Eqs. 7,8,9, t…
-
I encounter a similar issue to https://github.com/facebookresearch/ParlAI/issues/363
When I install PyTorch, clone ParlAI and then try to run one of the example commands, i.e. `python examples/train_…
k0105 updated
7 years ago
-
```
# choose RNN/GRU/LSTM cell
self.cell = rnn_cell.LSTMCell(self.memory_dim)
# embedding model
if not self.attention:
self.dec_outputs, self.dec_memory = seq2seq.…
-
Two problems happened when I used the latest Keras API.
1. After the model was trained, I saved the model architecture and weights. However, the reloaded model can't do prediction. Then I find I have …
-
Hi, I'm facing this issue since past two days trying to run the program. I'm running it on Ubuntu 16.04 with Nvidia 965m.
I have tried following ways:
Used both Python 2.7 and Python 3
Used tensor…
-
Because the call signature of `tf.concat` has changed to the one of the deprecated `tf.concat_v2`, the creation of a bidirectional RNN layer fails. This happens in either Version 1.2.1 or the latest m…
-
getting this error.. i suppose something to do with the recent changes in tensorflow ...i am using 1.1.0
ValueError: Attempt to reuse RNNCell with a different variable scope than its first use. F…
-
For bugs or installation issues, please provide the following information.
The more information you provide, the more likely people will be able to help you.
## Environment info
Operating System:…
-
The paper URL is https://www.researchgate.net/publication/305334401_Hierarchical_Attention_Networks_for_Document_Classification
-
Hello everyone, in the past days i've looked into many different issues posted about the possibility of implementing Bidirectional RNN in Keras. After digging a bit into it i came out with a simple so…