zhang943 / lpn-pytorch Goto Github PK
View Code? Open in Web Editor NEWLicense: MIT License
License: MIT License
Hello,I am very appreciate for your work. Here, I have a little question.
There is a function called generate_target in /lib/dataset/JointDataset.py, and the ground truth target is generated in 'Gaussian' form, but in your paper, beta-Soft-Argmax is presented to optimize the heatmap, suppressing the effect of the value close to zero.
Can you upload the training code for this amazing work? Thanks!
Has anyone reproduced successfully? I used the training files in HR-NET to train an LPN50, but the results were far from ideal.
hi,bro,do you have train.py
in this repo?
Hi @zhang943
I want to check your model on my rtsp video, so how to run inference. What is approximate speed FPS, i can get on Nvidia 1650 GPU?
Hello,
Sorry for the noob question, is this a top down or bottom up approach?
Hello, I want to test the inference speed of LPN50. Where is the inference speed in the log file?
if i want to test our method based on Simplebaseline, how to test the inference speed?
Thank you
thanks for your best work. but i have a question about "config.TEST.BIAS".
what is the function of this parameter?
in your paper, i don't find anything about the introduction about this parameter.
Looking forward to your reply
where is the code of Iterative Training Strategy, and how many steps is the appropriate choise?
why the speed of fps in the paper of v1 is 33 fps, but in v2 is 17fps
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.