feat(v2): complete Go inference and UI spike
This commit is contained in:
@@ -0,0 +1,63 @@
|
||||
package spike
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
|
||||
ort "github.com/yalue/onnxruntime_go"
|
||||
)
|
||||
|
||||
const (
|
||||
poseInputSize = 640
|
||||
poseInputCount = 1 * 3 * poseInputSize * poseInputSize
|
||||
poseOutputCount = 1 * 56 * 8400
|
||||
)
|
||||
|
||||
// RunPose executes the locked YOLO pose ONNX graph once using the CPU runtime.
|
||||
// The caller supplies absolute model and DLL paths so no camera credential or
|
||||
// machine-specific path is retained in V2 configuration or source.
|
||||
func RunPose(modelPath, runtimeDLLPath string, input []float32) ([]float32, error) {
|
||||
if len(input) != poseInputCount {
|
||||
return nil, fmt.Errorf("pose input length = %d, want %d", len(input), poseInputCount)
|
||||
}
|
||||
|
||||
ort.SetSharedLibraryPath(runtimeDLLPath)
|
||||
if err := ort.InitializeEnvironment(); err != nil {
|
||||
return nil, fmt.Errorf("initialize ONNX Runtime: %w", err)
|
||||
}
|
||||
defer func() { _ = ort.DestroyEnvironment() }()
|
||||
|
||||
inputTensor, err := ort.NewTensor(ort.NewShape(1, 3, poseInputSize, poseInputSize), input)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("create pose input tensor: %w", err)
|
||||
}
|
||||
defer func() { _ = inputTensor.Destroy() }()
|
||||
|
||||
outputTensor, err := ort.NewEmptyTensor[float32](ort.NewShape(1, 56, 8400))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("create pose output tensor: %w", err)
|
||||
}
|
||||
defer func() { _ = outputTensor.Destroy() }()
|
||||
|
||||
session, err := ort.NewAdvancedSession(
|
||||
modelPath,
|
||||
[]string{"images"},
|
||||
[]string{"output0"},
|
||||
[]ort.Value{inputTensor},
|
||||
[]ort.Value{outputTensor},
|
||||
nil,
|
||||
)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("open pose ONNX session: %w", err)
|
||||
}
|
||||
defer func() { _ = session.Destroy() }()
|
||||
|
||||
if err := session.Run(); err != nil {
|
||||
return nil, fmt.Errorf("run pose ONNX session: %w", err)
|
||||
}
|
||||
|
||||
output := outputTensor.GetData()
|
||||
if len(output) != poseOutputCount {
|
||||
return nil, fmt.Errorf("pose output length = %d, want %d", len(output), poseOutputCount)
|
||||
}
|
||||
return append([]float32(nil), output...), nil
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
package spike
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestRunPoseRejectsWrongInputLengthBeforeLoadingRuntime(t *testing.T) {
|
||||
_, err := RunPose("missing.onnx", "missing.dll", []float32{0})
|
||||
if err == nil {
|
||||
t.Fatal("RunPose accepted an input that is not 1x3x640x640")
|
||||
}
|
||||
if !strings.Contains(err.Error(), "input length") {
|
||||
t.Fatalf("RunPose error = %q, want input length error", err)
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,43 @@
|
||||
package spike
|
||||
|
||||
import "fmt"
|
||||
|
||||
// LetterboxBGRToNCHW converts one packed BGR frame into the RGB, CHW,
|
||||
// float32 tensor expected by the locked 640-pixel YOLO pose ONNX model.
|
||||
//
|
||||
// It intentionally uses nearest-neighbour scaling for this Spike. T-303
|
||||
// must replace or validate this preprocessing against the V1 implementation
|
||||
// before it becomes the V2 production preprocessing path.
|
||||
func LetterboxBGRToNCHW(frame []byte, width, height, target int) ([]float32, error) {
|
||||
if width <= 0 || height <= 0 || target <= 0 {
|
||||
return nil, fmt.Errorf("frame width, height and target must be positive")
|
||||
}
|
||||
if len(frame) != width*height*3 {
|
||||
return nil, fmt.Errorf("BGR frame length = %d, want %d", len(frame), width*height*3)
|
||||
}
|
||||
|
||||
scaleWidth := target
|
||||
scaleHeight := height * target / width
|
||||
if scaleHeight > target {
|
||||
scaleHeight = target
|
||||
scaleWidth = width * target / height
|
||||
}
|
||||
padX := (target - scaleWidth) / 2
|
||||
padY := (target - scaleHeight) / 2
|
||||
plane := target * target
|
||||
input := make([]float32, 3*plane)
|
||||
|
||||
for y := 0; y < scaleHeight; y++ {
|
||||
sourceY := y * height / scaleHeight
|
||||
for x := 0; x < scaleWidth; x++ {
|
||||
sourceX := x * width / scaleWidth
|
||||
source := (sourceY*width + sourceX) * 3
|
||||
destination := (padY+y)*target + padX + x
|
||||
input[destination] = float32(frame[source+2]) / 255.0
|
||||
input[plane+destination] = float32(frame[source+1]) / 255.0
|
||||
input[2*plane+destination] = float32(frame[source]) / 255.0
|
||||
}
|
||||
}
|
||||
|
||||
return input, nil
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
package spike
|
||||
|
||||
import "testing"
|
||||
|
||||
func TestLetterboxBGRToNCHWPlacesPixelInScaledImage(t *testing.T) {
|
||||
// One bright BGR pixel in a 2:1 frame should be resized into the centred
|
||||
// 640x320 image area. The remaining top/bottom area must stay black.
|
||||
frame := []byte{0, 0, 0, 255, 0, 0}
|
||||
|
||||
input, err := LetterboxBGRToNCHW(frame, 2, 1, 640)
|
||||
if err != nil {
|
||||
t.Fatalf("LetterboxBGRToNCHW returned an error: %v", err)
|
||||
}
|
||||
|
||||
const plane = 640 * 640
|
||||
if got := len(input); got != 3*plane {
|
||||
t.Fatalf("input length = %d, want %d", got, 3*plane)
|
||||
}
|
||||
if got := input[2*plane+159*640+320]; got != 0 {
|
||||
t.Fatalf("top padding blue channel = %v, want 0", got)
|
||||
}
|
||||
if got := input[0*plane+320*640+320]; got != 0 {
|
||||
t.Fatalf("red channel = %v, want 0", got)
|
||||
}
|
||||
if got := input[1*plane+320*640+320]; got != 0 {
|
||||
t.Fatalf("green channel = %v, want 0", got)
|
||||
}
|
||||
if got := input[2*plane+320*640+320]; got != 1 {
|
||||
t.Fatalf("blue channel = %v, want 1", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestLetterboxBGRToNCHWRejectsIncorrectFrameSize(t *testing.T) {
|
||||
_, err := LetterboxBGRToNCHW([]byte{0}, 2, 1, 640)
|
||||
if err == nil {
|
||||
t.Fatal("LetterboxBGRToNCHW accepted a truncated BGR frame")
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user