Is it possible to train the network using the latest Fastai and then load it using torch 1.6 so that it can be converted to coreML using coremltools 4.0?
You can get just the model weights using learn.save(). Then you should be able to load it in a PyTorch model that is defined in the same way. Just note that you will have to replicate the fastai inference code in pure PyTorch. I think if you are just using the model weights, training with the latest version of fastai will work.
Iām aware of the āNBā added to the docs page. Iām the founder of SeeMe.ai, so I can inform you that although there is no official pricing yet, Iām working hard on providing a generous free tier.