Hi, I need to create an application that will recognize a specific device model from a photo. I was thinking of a solution that would first detect the type of equipment in the photo, and then compare it with database photos of specific models. Based on appropriate probability (let’s say above 80%), the user would receive a true/false response. Does anyone know which transformer to use, and what the application flow should look like to work correctly?
1 Like
I’m guessing that use case will combine some of these, but perhaps you’ll need to train your model anyway.
It is quicker to find Spaces that are similar to your use case and to divert the flows, models, and code used there.
1 Like
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.