GithubHelp home page GithubHelp logo

yunxinli / multimodal-context-reasoning Goto Github PK

View Code? Open in Web Editor NEW
14.0 14.0 0.0 12.83 MB

A multimodal context reasoning approach that introduce the multi-view semantic alignment information via prefix tuning.

Python 100.00%

multimodal-context-reasoning's People

Contributors

yunxinli avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar

multimodal-context-reasoning's Issues

A problrm about the model "a_transformers"

Hello, I am having a problem running the code "run_PMR_ModCR.py" and the error is reported as follows:

Traceback (most recent call last):
  File "run_PMR_ModCR.py", line 21, in <module>
    from modeling.modeling_transfomres import BertImgModel
  File "/home/stormai/userfile/lizhengxue/WorkOnModCR/Multimodal-Context-Reasoning-main/modeling/modeling_transfomres.py", line 8, in <module>
    from a_transformers.modeling_bert import (BertEmbeddings,
ModuleNotFoundError: No module named 'a_transformers'

Where does the model "a_transformers" come from? And how do I use it?
In addition: What does the zip package "local_transformers.zip" do?
Thanks you!

file "

Hello.
Some missing files were found when i running the file "run_PMR_ModCR.py".

Traceback (most recent call last):
  File "run_PMR_ModCR.py", line 951, in <module>
    main()
  File "run_PMR_ModCR.py", line 861, in main
    train_dataset = PMR_ChunkAlign_Dataset_align_ensemble_T(tokenizer, gpt_tokenizer, roberta_tokenizer,
  File "/home/stormai/userfile/lizhengxue/WorkOnModCR/Multimodal-Context-Reasoning-main/Data/VCRChunkAlign.py", line 555, in __init__
    with open(clip_example_file, 'r') as file:
FileNotFoundError: [Errno 2] No such file or directory: 'pmr_data/clip_data/train_p_ori-clip.jsonl'

How do I access these files (such as clip_data/) ?

A question about PMR dataset

Hello.
I encountered the following error when running the run_PMR_ModCR.py folder:

Traceback (most recent call last):
  File "run_PMR_ModCR.py", line 930, in <module>
    main()
  File "run_PMR_ModCR.py", line 840, in main
    train_dataset = PMR_ChunkAlign_Dataset_align_ensemble_T(tokenizer, gpt_tokenizer, roberta_tokenizer,
  File "/home/stormai/userfile/lizhengxue/WorkOnModCR/Multimodal-Context-Reasoning-main/Data/VCRChunkAlign.py", line 542, in __init__
    self.VCR_annot_dict = pickle.load(open(VCR_example_file, 'rb'))
FileNotFoundError: [Errno 2] No such file or directory: 'pmr_data/ex_feature/train_CALeC_ori-o.pkl'

Where do I get the "train_CALeC_ori-o.pkl" file?

Question About the PMR dataset

In the original PMR paper: Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues. The dataset is divided into Original and Adversarial types, which consist of 12, 080 samples respectively. In your paper, which kind of dataset do you use? Looking forward to your reply.

file "clip_data/" not found

Hello.
Some missing files were found when i running the file "run_PMR_ModCR.py".

Traceback (most recent call last):
  File "run_PMR_ModCR.py", line 951, in <module>
    main()
  File "run_PMR_ModCR.py", line 861, in main
    train_dataset = PMR_ChunkAlign_Dataset_align_ensemble_T(tokenizer, gpt_tokenizer, roberta_tokenizer,
  File "/home/stormai/userfile/lizhengxue/WorkOnModCR/Multimodal-Context-Reasoning-main/Data/VCRChunkAlign.py", line 555, in __init__
    with open(clip_example_file, 'r') as file:
FileNotFoundError: [Errno 2] No such file or directory: 'pmr_data/clip_data/train_p_ori-clip.jsonl'

How do I access these files (such as clip_data/) ?

Multi-View-Reasoning-cold-start-1-0.19700910273081926-755.pth can not found

I use the checkpoint Multi-View-Reasoning-cold-start-1.pth instead to run PMR dataset. An error occurs when loading the model:

Error(s) in loading state_dict for Abstract_Specific: size mismatch for classifier.weight: copying a param with shape torch.Size([1, 2304]) from checkpoint, the shape in current model is torch.Size([1, 1536]).

Looking forwards to your reply

No such file or directory: 'pmr_data/ChunkMaskVal_v4_without_premise.pkl'

Hello, when I run python run_PMR_ModCR.py --do_train
"No such file or directory: 'pmr_data/ chunkmaskval_v4_without_prem.pkl '"Is displayed, and then I replace the above file with ChunkMaskTrain_v4_vcr.pkl in vcr_data and run it again, prompting clip missing. "No such file or directory: 'pmr_data/images/'" is displayed after deleting the clip code.

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.