Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Train on other dataset #47

Closed
carolchenyx opened this issue Mar 10, 2020 · 1 comment
Closed

Train on other dataset #47

carolchenyx opened this issue Mar 10, 2020 · 1 comment
Labels
question Further information is requested

Comments

@carolchenyx
Copy link

Thanks for your excellent work. If I want to train on my own dataset, how can I do? Thanks.

@stefanopini stefanopini added the question Further information is requested label Mar 13, 2020
@stefanopini
Copy link
Owner

Hi! To train on your own dataset, you just have to create a new class in datasets/ which inherits the class HumanPoseEstimation.

You have to implement the standard methods of the pytorch class Dataset and the additional method evaluate_accuracy(self, output, target, params=None). You can use the COCO dataset as a reference.

Let me know if you have any other question and, if you're working on a public dataset, feel free to send a pull request with the new dataset class! I'll be glad to add it in this repository

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants