Very interesting; as mentioned; this is very much an exploratory discussion from my side! All pointers and thoughts much appreciated.
Poking around in the code I’ve come across -
"Create a U-Net from a given architecture."
This model seems to have quite a bit of “bespoke” logic; but could weights trained with some other unet model be “re-used” and still give accurate results?
I don’t actually see a “unet” model in https://pytorch.org/docs/stable/torchvision/models.html … maybe they have a different naming there?
I think the a reasonable point of reference for the fastai ResNet model can be looked at here
"Resnet block from `ni` to `nh` with `stride`"
And again; it seems quite bespoke. My guess was it would require its own training cycle; but if its actually possible to re-use waits from “similar” pytorch models; that would be … good to know, and highlight I’ve got a lot more
understanding to get my head around!
Are those reasonable places to consider the definition of fastai unets and resnets?