Thank you, AncientCoder. I had a different use case in mind. You proposed using pre-made architectures that can be trained on the device (classifiers, regressors, etc.), but I meant something much lower-level than this.
For example, I would like to be able to create *.mlmodel that takes 2 inputs and just adds them together. Or any architecture using available ops. I can write MIL definition, but there is no way of turning it to the mlmodel/mlpackage in Swift, only using coremltools in Python.
It seems that MPSGraph is probably the best fit for my needs right now.
mlajtos
Users receive reputation points by contributing quality content to the forums.
Posts include post and replies published on the forums.
Post authors can mark replies as Accepted to indicate successful solutions.
Apple Developer Forums admins can mark replies as Apple Recommended to indicate an approved solution
Last seen
User for
Post
Replies
Boosts
Views
Activity
extension MPSDataType {
func description() -> String {
switch(self) {
case .float32:
return "f32"
case .int32:
return "i32"
// other...
default:
return "?"
}
}
}
The problem is with broadcasted template. Tensor with "static" shape works OK.
It seems, that this is indeed impossible due to MLIR dialect for Structured Control Flow.
https://llvm.discourse.group/t/scf-whileop-type-inference-with-dynamic-shapes/2529
This is awesome! Thank you very much.
I'll wait for the device then. 😎