-
This is a cross post from: https://stackoverflow.com/questions/45582185/getting-state-of-predictions-in-lstms
I have since tried to redo the model as:
```
batch_size = 64
model = Sequential()…
-
**Problem Summary**
I just tried to use `fine-tune` bidaf, and got the following error:
```
RuntimeError: index out of range at /Users/soumith/code/builder/wheel/pytorch-src/aten/src/TH/generic/TH…
-
Guys thanks for this interesting project. Appreciate the effort that you have put in here. I am trying out a few things but have a few doubts if I am doing things right.
I have 2 machines, each wit…
-
https://dx.doi.org/10.1093/bioinformatics/btw255
-
I have followed the tensorflow serving tutorial [mnist_saved_model.py][1]
and try to train and export a text-cnn-classifier model
The pipeline is
*embedding layer -> cnn->maxpol->cnn->drop…
-
I have a very large number of dimensions in my training data (5.4e06), which is very sparse. I wanted to try using the data raw as I could not find any embedding examples for continuous non-NLP tasks.…
-
when i am printing the imported summaries from the pickled file, its alright. It's fully printed in its encoded form. Vec_texts also prints fine. But vec_summaries_reduced and vec_texts_reduced return…
-
I have a model with which I can evaluate a dataset successfully:
```
python3.6 -m allennlp.run evaluate /Users/daniel/Dropbox/bidaf_train/bidaf-fine-tuned-iter\=5-learning-rate\=0_002/model.tar…
-
I have the following code -
def BuildMatrixFactorizationModel(usersCount, qaPairsCount):
left = Sequential()
left.add(Embedding(usersCount, EMBEDDING_DIM, input_length=1))
left.add(…
-
I am a new user of RNN and Keras for language mode. I found Keras accepts 3D tensor as input of RNN, which means word sequences have to be encoded into sequences of word vectors. The simplest is one h…