Git Product home page Git Product logo

d2-net's Introduction

D2-Net

[ICCV 2021] D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations. Arxiv link

Training D2-Net

Train on Thumos14 dataset using the following command.

python main.py --model-name Th14_release --dataset-name Thumos14reduced --num-class 20 --summary "D2net" --cuda

Citation

Kindly cite the following work if you find this repo useful.

@inproceedings{narayan2021d2,
  title={D2-Net: Weakly-supervised action localization via discriminative embeddings and denoised activations},
  author={Narayan, Sanath and Cholakkal, Hisham and Hayat, Munawar and Khan, Fahad Shahbaz and Yang, Ming-Hsuan and Shao, Ling},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2021}
}

Dependencies

This codebase has been tested on PyTorch1.7 and was based on the W-TALC repo found here.

d2-net's People

Contributors

naraysa avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar

Forkers

mymuli yangsenwxy artificial-intelligence-office

d2-net's Issues

Would you release your code?

Hello, your work is wonderful and interesting. I am so interested in your implementation. Would you release your source code for studying? Thanks a lot !!!

Could you provide the test_gt_segments.py file?

Hello, when I run the release code, I met the following error:

Iteration: 500, Loss: 0.059, LDis: 0.059, LDS: 0.000, LDV: 0.000
Testing test data point 0 of 212
Testing test data point 100 of 212
Testing test data point 200 of 212
Traceback (most recent call last):
  File "main.py", line 46, in <module>
    acc = test(itr, dataset, args, model, logger, device)
  File "/home/xxxx/Projects/_Reproduce/D2-Net-main/test.py", line 58, in test
    dmap, iou = dmAP(tcam_stack, dataset.path_to_annotations, args.activity_net, valid_id=dataset.lst_valid)
  File "/home/xxxx/Projects/_Reproduce/D2-Net-main/detectionMAP.py", line 324, in getDetectionMAP
    detections, gtsegments, temporal_labels, duration = getDetections(predictions, annotation_path, activity_net, valid_id)
  File "/home/xxxx/Projects/_Reproduce/D2-Net-main/detectionMAP.py", line 89, in getDetections
    gtseg = np.load('Thumos14reduced-Annotations/test_gt_segments.npy',allow_pickle=True)
  File "/home/xxxx/anaconda3/envs/co2/lib/python3.6/site-packages/numpy/lib/npyio.py", line 428, in load
    fid = open(os_fspath(file), "rb")
FileNotFoundError: [Errno 2] No such file or directory: 'Thumos14reduced-Annotations/test_gt_segments.npy'

Could you help me?

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.