-
-
We have trained QA net for our own question and answers data. But when we run it in demo mode for prediction it is giving different results for the same question.
Some times it picks correct answe…
-
For num_heads 1, hidden size 96, seems not faster then HKUST rnet ?
With batch size 64 , 1.42 batch/s while HKUST RNET with 2.4+ batch/s
Though HKUST RNET default use char dim only 8 , here we use …
-
So I'm running https://github.com/NLPLearn/QANet with tensorflow-upstream and I've had to cut my batch_size down to nothing to fit the model onto the GPU.
This is what happens when I try to train t…
-
First of all, thank you for this awesome work.
One suggestion. Include a separated column with a link for the source-code. This would help finding implementation that we can easily adopt and test a…
-
When trying to set the "pretrained_char" as True, the is a tensor reshape size conflict.
```
glove_char_file = os.path.join('data/glove', "glove.840B.300d-char.txt")
flags.DEFINE_string("glove_…
-
Adding `model.save('xxxx.h5')` in `QANet_fit_demo.py` fails with this stack.
Any ideas why that is happening?
```
Traceback (most recent call last):
File "QANet_fit_demo.py", line 26, in
…
-
I am experiencing a problem with bundler 1.2.1, wherein if I run bundle install, rake 10.0.0 is installed into my global gemset.
If I remove bundler 1.2.1 and remain on 1.2.0 with the same gemfile/g…
-
TypeError: Cannot set property 'restangularRoute' of null
at restangularizeBase (http://localhost:3000/assets/restangular.js?body=1:444:56)
at restangularizeElem (http://localhost:3000/assets/…