According to CoreMLTools documentation if you convert to ML Program format you could use sparse representation - https://coremltools.readme.io/docs/compressing-ml-program-weights
It should be interesting to know if this is supported on both NE, GPU and CPU.
Post
Replies
Boosts
Views
Activity
Were you able to solve the key generation issue? I'm having the same problem and I signed in with the same Apple ID