Giter VIP home page Giter VIP logo

dukenet's People

Contributors

chuanmeng avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

dukenet's Issues

Interactive mode

Is there a way to check inference for a new sample of knowledge background sentences, and possibly use it like an interaction mode?

What modifications in the code would be required to test it like in an interactive fashion?
Thanks!

Unexpected key(s) in state_dict using pretrained model

Hi, I get the following error while trying to run inference with the pretrained model. Not sure how to resolve this, any help would be appreciated. Thanks!

CUDA_version:10.1
cudnn_version:7603
Vocabulary size 30522
The number of dev_samples: 8814
The number of test_seen_samples: 4336
The number of test_unseen_samples: 4370
Start inference at epoch d_3
Traceback (most recent call last):
  File "DukeNet/Run.py", line 321, in <module>
    inference(args)
  File "DukeNet/Run.py", line 261, in inference
    inference(args.dataset, i)
  File "DukeNet/Run.py", line 206, in inference
    model.load_state_dict(torch.load(file)["model"])
  File "/home/bakhtiyar/anaconda3/envs/dukenet-2/lib/python3.6/site-packages/torch/nn/modules/module.py", line 830, in load_state_dict
    self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for DukeNet:
	Missing key(s) in state_dict: "enc.enc.embeddings.position_ids", "dec.embedding.0.position_ids", "dec.embedding.0.word_embeddings.weight", "dec.embedding.0.position_embeddings.weight", "dec.embedding.0.token_type_embeddings.weight", "dec.embedding.0.LayerNorm.weight", "dec.embedding.0.LayerNorm.bias", "dec.embedding.1.pe". 
	Unexpected key(s) in state_dict: "dec.embedding.word_embeddings.weight", "dec.embedding.position_embeddings.weight", "dec.embedding.token_type_embeddings.weight", "dec.embedding.LayerNorm.weight", "dec.embedding.LayerNorm.bias". 

About the environment requirement

Hi, thanks for the open source of Dukenet.

I try to run this code but got segmentation fault (core dumped). It seems that the dependency of some python libs (maybe pytorch/transformers/cudatoolkit/cudnn version) is not compatible with the code.

I wonder if you can provide the specific versions of the python libs needed for the code.

I appreciate for that a lot.

Best.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.