-
Making issue from comment https://github.com/keras-team/keras/issues/10080#issuecomment-394640409 at #10080.
When converting weights between CuDNNGRU and GRU which is wrapped in TimeDistributed the…
-
## Issue description
I have a sequence to sequence model trained with pytorch 0.3.0.post4. It gave reasonable outputs when queried at the time, and I have since downloaded the model onto my compute…
-
A small bug does not allow to train the network when _Bidirectional_ is set to _False_.
In "model.py", on line 135, _Bidirectional_ should be set to "_False_": [Line 135](https://github.com/EdGENet…
-
We are planning to build Deep Speech 2 (DS2) \[[1](#references)\], a powerful Automatic Speech Recognition (ASR) engine, on PaddlePaddle. For the first-stage plan, we have the following short-term go…
-
I am trying to use the wmt_17 zh-en model. I am currently able to do translation using nematus but it's slow, now I am trying to do the same with marian, but I am unable to figure out the values of va…
-
I am trying to train a model and each time after few seconds I get the following error:
[2018-05-30 11:41:00] [config] after-batches: 0
[2018-05-30 11:41:00] [config] after-epochs: 0
[2018-05-30…
-
It would be important to specify which dataset Yunitator is trained with (or am I the only one who is missing the info?), because users can try out samples that may be included in the training dataset…
-
What can be the baseline model for the squad assuming that you get the hidden states of the context and question using a bidirectional GRU separately over context and questions?
Also did you one-hot…
-
Hello, my task is grammatical error correction, where the source and target sentence is the same language.
Here is the example:
The source is the erroneous tokenized sentence, e.x. "I loves opennmt…
-
Analogous to CuDNN RNN nested in Bidirectional: #8908
In addition same bug as in: Convert h5py Dataset to np.array before preprocess_weights_for_loading (#9662)
I've already wrote a fix and I'll…