EDGE FDE
IntermediateFrom Metal to Core AI Model
Start at Metal shaders. Walk the clothing-classifier stack backwards until you return to the original pipeline lesson.
For people who finished, or quickly looked through, PyTorch to Core AI in Xcode.
Lessons
Key concepts
- This course walks backwards from Metal and Apple silicon up to the original pipeline.
- The contract is
clothing.aimodel, functionmain,image[1, 1, 28, 28]float32 0-1,logits[1, 10]. - Core AI can run on CPU, GPU, or Neural Engine. Metal is how the GPU runs work.
- Each layer above must give the layer below shapes, types, supported ops, and prepare once.
Takeaways
- You can read the clothing classifier from the chip up, not only from training down.
- When something breaks, ask which lower-layer requirement failed before you blame the UI.
- You can reopen the original pipeline and read every forward arrow as a requirement for the layer below.
Agent briefs
FAQ
What does this course walk?
It starts at Metal shaders and walks the clothing-classifier stack backwards until you return to the original pipeline lesson.
What is the clothing model contract?
clothing.aimodel, function main, image [1, 1, 28, 28] float32 0-1, logits [1, 10].
Where does Core AI run?
Core AI can run on CPU, GPU, or Neural Engine. Metal is how the GPU runs work.
Why walk the stack backwards?
Each layer above must give the layer below shapes, types, supported ops, and prepare once. When something breaks, ask which lower-layer requirement failed before you blame the UI.
Do I need the PyTorch to Core AI course first?
This course is for people who finished, or quickly looked through, PyTorch to Core AI in Xcode.