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

How to train own model and annotations for this? #69

Open
sharon-samson opened this issue Feb 25, 2021 · 2 comments
Open

How to train own model and annotations for this? #69

sharon-samson opened this issue Feb 25, 2021 · 2 comments

Comments

@sharon-samson
Copy link

Hi Iam currently working on a research project, and it will be helpful if some one explain how can we train our own model and how to create its annotation files..

@sharon-samson sharon-samson changed the title How can we train own model and annotations for this? How to train own model and annotations for this? Feb 25, 2021
@HamzaZwairy
Copy link

HamzaZwairy commented Mar 14, 2021

@sharon-samson Hi, I don't know if I'm too late or not but I think that this tutorial in PyTorch is helpful. Just create your own dataset class and go on with the tutorial, it applies Mask-RCNN which should do a decent job in an instance segmentation task ( it will also output the bounding boxes and their labels ).

https://pytorch.org/tutorials/intermediate/torchvision_tutorial.html

@sharon-samson
Copy link
Author

I got segmented output. How can I make landmark points on it?

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

No branches or pull requests

2 participants