Hi there. I have two YOLOv5s tflite models which recognize different classes (one with 80, and one with just one). Is there a way to use transfer learning to add the class from the smaller one to the bigger one in any way? I don’t have the resources to train the model on a combined dataset, so just wondering if there is another way to do combine both models. Thank you!
I’m also fine with training locally, if this can’t be done on Edge Impulse.
Can this be done with BYOM? How exactly does BYOM work?
Hi @SMCoder775,
You cannot run two models at the same time right now if you deploy with Edge Impulse. If you train a single model locally, you can use BYOM to convert the model to compile/optimize/deploy to an embedded system. Please see the documentation for BYOM here.