Code Monkey home page Code Monkey logo

keypoints's People

Contributors

akimoto-cris avatar hackiey 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 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 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 avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar

Forkers

110awesome foooder sharpoo7 hzhang57 zengai chinacobby baipdiw akimoto-cris ming6383 shorelake alexadlu louisnust zhaowangbu oujieww gjylt xrosliang jackqu priyasundaresan githubfragments yjq631160551 cyblearn yangtao47 zephyrii qiuhuan

keypoints's Issues

Question about the different image size in training and testing

Hi, thank you for providing this excellent code.
I have some questions about the different image size at training and testing.
In training, you calculate loss based on the upsampled output, which has the same image size as the input image. However, in testing(prediction), you calculate the keypoints based on the results before Upsampling.
I was wondering why you do this in testing time? For efficiency or something else?
Look forward to your reply, thank you!

Pre-trained model

Hi @hackiey,

I am planning to use this key-point detector in one of my projects. I need it for inference only. Do you have or plan to release the pre-trained model that can be used for inference?

Thanks!

差评

Why don’t you include the reference link of that paper? 😡

question about the model.py

Hi @hackiey ,
Thanks for your code. But I still have a question about the network in your implement.
Paper said that "we employ atrous convolution to generate the 3 · K predictions", but in your model.py, you used nn.ConvTranspose2d. Is these two methods same?

keypoints/src/model.py

Line 24 in a676ef0

self.conv_transpose = nn.ConvTranspose2d(self.num_outputs, self.num_outputs, kernel_size=32, stride=8)

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.