coremlcompiler

func Compile ¶

func Compile(inputPath, outputPath string) error

Compile compiles a CoreML model package (.mlpackage) or model file (.mlmodel) into a compiled bundle (.mlmodelc) at outputPath.

Only mlprogram models (spec version 5+) are supported. Legacy NeuralNetwork models must be converted to the mlprogram format before compilation (e.g. via coremltools.convert with convert_to="mlprogram").

func CompileMILText ¶

func CompileMILText(milText string, specVersion int32, desc ModelDescription, weightRoot, outputPath string) error

CompileMILText compiles an already-emitted mlprogram MIL text into a compiled bundle at outputPath.

desc names the model inputs, outputs, and states stored in coremldata.bin and metadata.json. weightRoot, when non-empty, is copied into the bundle preserving relative paths, so BLOBFILE paths like "@model_path/weights/..." resolve correctly at runtime.

package main

import (
	"fmt"
	"os"
	"path/filepath"

	"github.com/tmc/apple/x/coremlcompiler"
)

func main() {
	tmpDir, err := os.MkdirTemp("", "coremlcompiler-example-*")
	if err != nil {
		fmt.Println(err)
		return
	}
	defer os.RemoveAll(tmpDir)

	milText := `program(1.3) {
    func main<ios18>(tensor<fp16, [1, 8]> x) {
    } -> (x);
}`
	desc := coremlcompiler.ModelDescription{
		Inputs:  []coremlcompiler.FeatureDescription{{Name: "x"}},
		Outputs: []coremlcompiler.FeatureDescription{{Name: "x"}},
	}
	err = coremlcompiler.CompileMILText(milText, 8, desc, "", filepath.Join(tmpDir, "model.mlmodelc"))
	if err != nil {
		fmt.Println(err)
	}
}

Output:

func CompileMLModelAtURL ¶ added in v0.5.4

func CompileMLModelAtURL(sourcePath string) (string, error)

CompileMLModelAtURL uses [MLModel compileModelAtURL:error:] to compile a .mlpackage or .mlmodel to a .mlmodelc directory. Only available on darwin.

func CompileMLProgram ¶

func CompileMLProgram(modelProto []byte, weightDir, outputPath string) error

CompileMLProgram compiles an mlprogram model from already-parsed components. This is useful when you have the model proto bytes and weight directory available separately.

func CompileToTemp ¶

func CompileToTemp(inputPath string) (string, error)

CompileToTemp compiles a model to a temporary directory, returning the path to the compiled .mlmodelc bundle. The directory is placed under os.TempDir() and named by a hash of the input path for implicit caching.

func EncodeModel ¶ added in v0.5.0

func EncodeModel(m *Model) []byte

EncodeModel encodes a Model to protobuf wire format.

func WriteMILBlob ¶ added in v0.5.4

func WriteMILBlob(entries []BlobEntry) (data []byte, offsets []uint64)

WriteMILBlob builds a MIL Blob Storage v2 weight file from the given entries. Returns the complete file bytes and the BLOBFILE offsets (one per entry) that should be used in MIL text.

func WriteMLPackage ¶ added in v0.5.0

func WriteMLPackage(dir string, modelProto []byte, weightSrc string) error

WriteMLPackage creates a .mlpackage directory at dir containing the given model protobuf and optional weights. The directory can be read back by readMLPackage or passed to MLModel.compileModelAtURL:.

The layout matches Apple's coremltools format:

dir/
├── Manifest.json
└── Data/
    └── com.apple.CoreML/
        ├── model.mlmodel     (modelProto bytes)
        └── weights/          (copied from weightSrc if provided)

Manifest paths use "com.apple.CoreML/..." (without Data/ prefix); the Data/ directory is implicit when resolving paths on disk.

If weightSrc is non-empty and is a directory, its contents are copied into the package's CoreML directory preserving relative paths. If weightSrc is a single file, it is copied as weights/weight.bin.