Hello, I would like to know more about Multi-label classification model. I am planning to use this model in my final thesis. Is there any possibilities to learn more about the understructure of this model? Such as, which algorithms does this model use? I checked a lot of resources, GitHub and many websites but couldn’t be able to find any information. Any help would be appreciated.
Hello - for your thesis, you can say it is similar to Vision Transformer (ViT). There is customization by Roboflow which is why we ask people to cite Roboflow in research and academic environments.
1 Like
We would like to employ your systems(roboflow) in our academic study, for this reason we need the details of the algorithms employed, could you give us brief information about the model parameters (ie the patch size for VIT) or at least provide references of related studies for roboflow. Also, definitely we are going to cite roboflow. 
Here is my contact email if needed: berkanozgur@hotmail.com
Thanks in advance
We use google/vit-base-patch16-224-in21k. This is as much as we can share. Thank you for understanding.
1 Like