Git Product home page Git Product logo

ca-captioner's Introduction

Paper link: CA-Captioner: A novel concentrated attention for image captioning. https://doi.org/10.1016/j.eswa.2024.123847

citation: @article{YANG2024123847, title = {CA-Captioner: A novel concentrated attention for image captioning}, journal = {Expert Systems with Applications}, volume = {250}, pages = {123847}, year = {2024}, issn = {0957-4174}, doi = {https://doi.org/10.1016/j.eswa.2024.123847}, url = {https://www.sciencedirect.com/science/article/pii/S0957417424007139}, author = {Xiaobao Yang and Yang Yang and Junsheng Wu and Wei Sun and Sugang Ma and Zhiqiang Hou}, keywords = {Image captioning, Transformer, Concentrated attention, Sparse mechanism, Positional encoding}, }

ca-captioner's People

Contributors

y78h11b09 avatar

Stargazers

 avatar

Watchers

Kostas Georgiou avatar  avatar

Forkers

yangyanggit89

ca-captioner's Issues

关于梯度计算

我尝试使用您的代码,但是显示LSM部分,ratio不能正常计算梯度,我尝试在loss.backward()后面添加程序查看每一层的梯度值,但是显示ratio的梯度值为None。
貌似这种现象是因为self.ratio在使用过程中,经过由tensor转为int的过程,导致梯度无法跟踪。
想问一下您使用哪个版本的torch,或者是否遇到过这个问题

关于训练和验证时候传入到解码器的问题

作者您好,我想问下 我观察到你的代码 训练的传入解码器为swin提取结束后的特征图,但是并未传入后续经过编码器处理的数据给解码器,但是在验证的时候确实将编码器处理后传入到解码器,我这样理解是正确的吗,分别对应这两行代码:
训练:outputs, _ = decoder(enc_outputs, dec_inputs, dec_inputs_len)
验证:dec_out,,=decoder.decode(k_prev_words,dec_partial_inputs_len,enc_output)

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.