Skip to content

issues Search Results · repo:allenai/deep_qa language:Python

Filter by

52 results
 (60 ms)

52 results

inallenai/deep_qa (press backspace or delete to remove)

allenai/deep_qa
Testing the model and getting answer to a new question

Hi, I have trained the bidaf model on squad, and I have the following questions 1. predictions = score_dataset( [..]reading_comprehension/bidaf_squad.json ) gives: Traceback (most recent call last): ...
  • marilenaoita
  • 2
  • Opened 
    on Apr 22, 2018
  • #413

allenai/deep_qa
Find small dimension typo in reading_comprehension/bidirectional_attention.py

Hi, first of all, thank you very much for your work! While implementing your code, I found in bidirectional_attention.py line 128, passage_question_vectors = weighted_sum_layer([encoded_question, passage_question_attention]) ...
  • felizxia
  • 3
  • Opened 
    on Mar 25, 2018
  • #412

allenai/deep_qa
Getting a nan softmax loss

I followed the instructions and started training on the Squad Dataset. It started off well but then the loss became a nan. What could be the possible reason and how can I correct it ? `657/1474 [============ ...
  • bhavikajalli
  • 1
  • Opened 
    on Nov 7, 2017
  • #411

allenai/deep_qa
evaluate_model() gives parsing error

I am trying to evaluate a model using evaluate_model() evaluate_model( some.json ) but it gives a ParseException. some.json- { model_class : BidirectionalAttentionFlow , model_serialization_prefix ...
  • mohitbadwal
  • 1
  • Opened 
    on Jul 27, 2017
  • #410

allenai/deep_qa
Cannot run `bidaf_squad.json`

Should I be able to run the following out of the box or do I need to train first? # python scripts/run_model.py example_experiments/reading_comprehension/bidaf_squad.json test 2017-06-20 16:36:40,791 ...
  • schmmd
  • 3
  • Opened 
    on Jun 20, 2017
  • #408

allenai/deep_qa
Better API around continuing training

Currently, if you want to load a model trained on one dataset and continue training, you can kind of do that, but it will end up overwriting the model that you loaded, which is a problem. We should add ...
Easy
New API feature
P1
  • matt-gardner
  • Opened 
    on Jun 16, 2017
  • #403

allenai/deep_qa
scripts for data processing?

Do you have script files for processing raw dataset such as snli_1.0 to processed/{train,dev}.tsv in your example json file?
  • dykang
  • 2
  • Opened 
    on Jun 1, 2017
  • #382

allenai/deep_qa
Use virtualenv instead of conda

We use conda to create a consistent environment for Python. Is there a reason we use conda over virtualenv? I was reading the AI2 Python Guide and it recommends using virtualenv. Are there any concerns ...
  • schmmd
  • 6
  • Opened 
    on Jun 1, 2017
  • #381

allenai/deep_qa
Unpin Sphinx version

See #362. We had to pin the sphinx version because of a conflict with how we re using python s logging functionality. We need to fix this somehow.
API clean up
Easy
P1
  • matt-gardner
  • 1
  • Opened 
    on May 16, 2017
  • #363

allenai/deep_qa
Generator re-pads shuffled instances which are already padded

screen shot 2017-05-16 at 11 00 04 am Training using the data generator results in a slow down due to incremental padding from the noise introduced during shuffling.
bug
  • DeNeutoy
  • 2
  • Opened 
    on May 16, 2017
  • #360
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub