Closed nikhilbyte closed 3 years ago
Hello, I was working on a project where I'm required to encode two images for finding multiclass semantic difference between them. Can you please tell which one should I use(with Channel attention or without)? and what changes should i consider?
Hi, @nikhilbyte I don't know the specifics of your data and tasks, but maybe you can do it by changing the last few layers of the model.
Hello, I was working on a project where I'm required to encode two images for finding multiclass semantic difference between them. Can you please tell which one should I use(with Channel attention or without)? and what changes should i consider?