private static int DetectYoloV3(NcnnDotNet.OpenCV.Mat bgr, List <Object> objects)
{
using (var yolov3 = new Net())
{
if (Ncnn.IsSupportVulkan)
{
yolov3.Opt.UseVulkanCompute = true;
}
// original pretrained model from https://github.com/eric612/MobileNet-YOLO
// param : https://drive.google.com/open?id=1V9oKHP6G6XvXZqhZbzNKL6FI_clRWdC-
// bin : https://drive.google.com/open?id=1DBcuFCr-856z3FRQznWL_S5h-Aj3RawA
// the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
yolov3.LoadParam("mobilenetv2_yolov3.param");
yolov3.LoadModel("mobilenetv2_yolov3.bin");
const int targetSize = 352;
var imgW = bgr.Cols;
var imgH = bgr.Rows;
using (var @in = Mat.FromPixelsResize(bgr.Data, PixelType.Bgr, bgr.Cols, bgr.Rows, targetSize, targetSize))
{
var meanVals = new[] { 127.5f, 127.5f, 127.5f };
var normVals = new[] { 0.007843f, 0.007843f, 0.007843f };
@in.SubstractMeanNormalize(meanVals, normVals);
using (var ex = yolov3.CreateExtractor())
{
ex.SetNumThreads(4);
ex.Input("data", @in);
using (var @out = new Mat())
{
ex.Extract("detection_out", @out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.Clear();
for (var i = 0; i < @out.H; i++)
{
var values = @out.Row(i);
var @object = new Object();
@object.Label = (int)values[0];
@object.Prob = values[1];
@object.Rect.X = values[2] * imgW;
@object.Rect.Y = values[3] * imgH;
@object.Rect.Width = values[4] * imgW - @object.Rect.X;
@object.Rect.Height = values[5] * imgH - @object.Rect.Y;
objects.Add(@object);
}
}
}
}
}
return(0);
}
private static int DetectMobileNetV3(NcnnDotNet.OpenCV.Mat bgr, List <Object> objects)
{
using (var mobilenetV3 = new Net())
{
if (Ncnn.IsSupportVulkan)
{
mobilenetV3.Opt.UseVulkanCompute = true;
}
// converted ncnn model from https://github.com/ujsyehao/mobilenetv3-ssd
mobilenetV3.LoadParam("mobilenetv3_ssdlite_voc.param");
mobilenetV3.LoadModel("mobilenetv3_ssdlite_voc.bin");
const int targetSize = 300;
var imgW = bgr.Cols;
var imgH = bgr.Rows;
using var @in = Mat.FromPixelsResize(bgr.Data, PixelType.Bgr2Rgb, bgr.Cols, bgr.Rows, targetSize, targetSize);
var meanVals = new[] { 123.675f, 116.28f, 103.53f };
var normVals = new[] { 1.0f, 1.0f, 1.0f };
@in.SubstractMeanNormalize(meanVals, normVals);
using var ex = mobilenetV3.CreateExtractor();
ex.SetLiteMode(true);
ex.SetNumThreads(4);
ex.Input("input", @in);
using var @out = new Mat();
ex.Extract("detection_out", @out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.Clear();
for (var i = 0; i < @out.H; i++)
{
var values = @out.Row(i);
var @object = new Object();
@object.Label = (int)values[0];
@object.Prob = values[1];
// filter out cross-boundary
var x1 = Clamp(values[2] * targetSize, 0.0f, targetSize - 1) / targetSize * imgW;
var y1 = Clamp(values[3] * targetSize, 0.0f, targetSize - 1) / targetSize * imgH;
var x2 = Clamp(values[4] * targetSize, 0.0f, targetSize - 1) / targetSize * imgW;
var y2 = Clamp(values[5] * targetSize, 0.0f, targetSize - 1) / targetSize * imgH;
@object.Rect.X = x1;
@object.Rect.Y = y1;
@object.Rect.Width = x2 - x1;
@object.Rect.Height = y2 - y1;
objects.Add(@object);
}
}
return(0);
}
private static int DetectYoloV2(NcnnDotNet.OpenCV.Mat bgr, List <Object> objects)
{
using (var yolov2 = new Net())
{
if (Ncnn.IsSupportVulkan)
{
yolov2.Opt.UseVulkanCompute = true;
}
// original pretrained model from https://github.com/eric612/MobileNet-YOLO
// https://github.com/eric612/MobileNet-YOLO/blob/master/models/yolov2/mobilenet_yolo_deploy.prototxt
// https://github.com/eric612/MobileNet-YOLO/blob/master/models/yolov2/mobilenet_yolo_deploy_iter_80000.caffemodel
// the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
yolov2.LoadParam("mobilenet_yolo.param");
yolov2.LoadModel("mobilenet_yolo.bin");
const int targetSize = 416;
var imgW = bgr.Cols;
var imgH = bgr.Rows;
using var @in = Mat.FromPixelsResize(bgr.Data, PixelType.Bgr, bgr.Cols, bgr.Rows, targetSize, targetSize);
// the Caffe-YOLOv2-Windows style
// X' = X * scale - mean
var meanVals = new[] { 1.0f, 1.0f, 1.0f };
var normVals = new[] { 0.007843f, 0.007843f, 0.007843f };
@in.SubstractMeanNormalize(null, normVals);
@in.SubstractMeanNormalize(meanVals, null);
using var ex = yolov2.CreateExtractor();
ex.SetNumThreads(4);
ex.Input("data", @in);
using var @out = new Mat();
ex.Extract("detection_out", @out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.Clear();
for (var i = 0; i < @out.H; i++)
{
var values = @out.Row(i);
var @object = new Object();
@object.Label = (int)values[0];
@object.Prob = values[1];
@object.Rect.X = values[2] * imgW;
@object.Rect.Y = values[3] * imgH;
@object.Rect.Width = values[4] * imgW - @object.Rect.X;
@object.Rect.Height = values[5] * imgH - @object.Rect.Y;
objects.Add(@object);
}
}
return(0);
}
private static int DetectPeleeNet(NcnnDotNet.OpenCV.Mat bgr, List <Object> objects, NcnnDotNet.Mat resized)
{
using (var peleenet = new Net())
{
if (Ncnn.IsSupportVulkan)
{
peleenet.Opt.UseVulkanCompute = true;
}
// model is converted from https://github.com/eric612/MobileNet-YOLO
// and can be downloaded from https://drive.google.com/open?id=1Wt6jKv13sBRMHgrGAJYlOlRF-o80pC0g
// the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
peleenet.LoadParam("pelee.param");
peleenet.LoadModel("pelee.bin");
const int targetSize = 300;
var imgW = bgr.Cols;
var imgH = bgr.Rows;
using var @in = Mat.FromPixelsResize(bgr.Data, PixelType.Bgr, bgr.Cols, bgr.Rows, targetSize, targetSize);
var meanVals = new[] { 103.9f, 116.7f, 123.6f };
var normVals = new[] { 0.017f, 0.017f, 0.017f };
@in.SubstractMeanNormalize(meanVals, normVals);
using var ex = peleenet.CreateExtractor();
//ex.SetNumThreads(4);
ex.Input("data", @in);
using var @out = new Mat();
ex.Extract("detection_out", @out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.Clear();
for (var i = 0; i < @out.H; i++)
{
var values = @out.Row(i);
var @object = new Object();
@object.Label = (int)values[0];
@object.Prob = values[1];
@object.Rect.X = values[2] * imgW;
@object.Rect.Y = values[3] * imgH;
@object.Rect.Width = values[4] * imgW - @object.Rect.X;
@object.Rect.Height = values[5] * imgH - @object.Rect.Y;
objects.Add(@object);
}
using var segOut = new Mat();
ex.Extract("sigmoid", segOut);
Ncnn.ResizeBilinear(segOut, resized, imgW, imgH);
}
return(0);
}
private static int DetectMobileNetV2(NcnnDotNet.OpenCV.Mat bgr, List <Object> objects)
{
using (var mobilenetV2 = new Net())
{
if (Ncnn.IsSupportVulkan)
{
mobilenetV2.Opt.UseVulkanCompute = true;
}
// ToDo: Support Custom Layer from C#
//mobilenetV2.register_custom_layer("Silence", Noop_layer_creator);
// original pretrained model from https://github.com/chuanqi305/MobileNetv2-SSDLite
// https://github.com/chuanqi305/MobileNetv2-SSDLite/blob/master/ssdlite/voc/deploy.prototxt
// the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
mobilenetV2.LoadParam("mobilenetv2_ssdlite_voc.param");
mobilenetV2.LoadModel("mobilenetv2_ssdlite_voc.bin");
const int targetSize = 300;
var imgW = bgr.Cols;
var imgH = bgr.Rows;
using var @in = Mat.FromPixelsResize(bgr.Data, PixelType.Bgr, bgr.Cols, bgr.Rows, targetSize, targetSize);
var meanVals = new[] { 127.5f, 127.5f, 127.5f };
var normVals = new[] { (float)(1.0 / 127.5), (float)(1.0 / 127.5), (float)(1.0 / 127.5) };
@in.SubstractMeanNormalize(meanVals, normVals);
using var ex = mobilenetV2.CreateExtractor();
ex.SetLiteMode(true);
ex.SetNumThreads(4);
ex.Input("data", @in);
using var @out = new Mat();
ex.Extract("detection_out", @out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.Clear();
for (var i = 0; i < @out.H; i++)
{
var values = @out.Row(i);
var @object = new Object();
@object.Label = (int)values[0];
@object.Prob = values[1];
@object.Rect.X = values[2] * imgW;
@object.Rect.Y = values[3] * imgH;
@object.Rect.Width = values[4] * imgW - @object.Rect.X;
@object.Rect.Height = values[5] * imgH - @object.Rect.Y;
objects.Add(@object);
}
}
return(0);
}
private static int DetectSqueezeNet(NcnnDotNet.OpenCV.Mat bgr, List <Object> objects)
{
using (var squeezenet = new Net())
{
if (Ncnn.IsSupportVulkan)
{
squeezenet.Opt.UseVulkanCompute = true;
}
// original pretrained model from https://github.com/chuanqi305/SqueezeNet-SSD
// squeezenet_ssd_voc_deploy.prototxt
// https://drive.google.com/open?id=0B3gersZ2cHIxdGpyZlZnbEQ5Snc
// the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
squeezenet.LoadParam("squeezenet_ssd_voc.param");
squeezenet.LoadModel("squeezenet_ssd_voc.bin");
const int targetSize = 300;
var imgW = bgr.Cols;
var imgH = bgr.Rows;
using var @in = Mat.FromPixelsResize(bgr.Data, PixelType.Bgr, bgr.Cols, bgr.Rows, targetSize, targetSize);
var meanVals = new[] { 104f, 117f, 123f };
@in.SubstractMeanNormalize(meanVals, null);
using var ex = squeezenet.CreateExtractor();
ex.SetNumThreads(4);
ex.Input("data", @in);
using var @out = new Mat();
ex.Extract("detection_out", @out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.Clear();
for (var i = 0; i < @out.H; i++)
{
var values = @out.Row(i);
var @object = new Object();
@object.Label = (int)values[0];
@object.Prob = values[1];
@object.Rect.X = values[2] * imgW;
@object.Rect.Y = values[3] * imgH;
@object.Rect.Width = values[4] * imgW - @object.Rect.X;
@object.Rect.Height = values[5] * imgH - @object.Rect.Y;
objects.Add(@object);
}
}
return(0);
}
private static int DetectMobileNet(NcnnDotNet.OpenCV.Mat bgr, List <Object> objects)
{
using (var mobilenet = new Net())
{
if (Ncnn.IsSupportVulkan)
{
mobilenet.Opt.UseVulkanCompute = true;
}
// model is converted from https://github.com/chuanqi305/MobileNet-SSD
// and can be downloaded from https://drive.google.com/open?id=0ByaKLD9QaPtucWk0Y0dha1VVY0U
// the ncnn model https://github.com/nihui/ncnn-assets/tree/master/models
mobilenet.LoadParam("mobilenet_ssd_voc_ncnn.param");
mobilenet.LoadModel("mobilenet_ssd_voc_ncnn.bin");
const int targetSize = 300;
var imgW = bgr.Cols;
var imgH = bgr.Rows;
using var @in = Mat.FromPixelsResize(bgr.Data, PixelType.Bgr, bgr.Cols, bgr.Rows, targetSize, targetSize);
var meanVals = new[] { 127.5f, 127.5f, 127.5f };
var normVals = new[] { (float)(1.0 / 127.5), (float)(1.0 / 127.5), (float)(1.0 / 127.5) };
@in.SubstractMeanNormalize(meanVals, normVals);
using var ex = mobilenet.CreateExtractor();
//ex.SetNumThreads(4);
ex.Input("data", @in);
using var @out = new Mat();
ex.Extract("detection_out", @out);
// printf("%d %d %d\n", out.w, out.h, out.c);
objects.Clear();
for (var i = 0; i < @out.H; i++)
{
var values = @out.Row(i);
var @object = new Object();
@object.Label = (int)values[0];
@object.Prob = values[1];
@object.Rect.X = values[2] * imgW;
@object.Rect.Y = values[3] * imgH;
@object.Rect.Width = values[4] * imgW - @object.Rect.X;
@object.Rect.Height = values[5] * imgH - @object.Rect.Y;
objects.Add(@object);
}
}
return(0);
}
// copy from src/layer/proposal.cpp
private static Mat GenerateAnchors(int baseSize, Mat ratios, Mat scales)
{
var numRatio = ratios.W;
var numScale = scales.W;
var anchors = new Mat();
anchors.Create(4, numRatio * numScale);
var cx = baseSize * 0.5f;
var cy = baseSize * 0.5f;
for (var i = 0; i < numRatio; i++)
{
var ar = ratios[i];
var rW = (int)Math.Round(baseSize / Math.Sqrt(ar));
var rH = (int)Math.Round(rW * ar); //round(baseSize * sqrt(ar));
for (var j = 0; j < numScale; j++)
{
var scale = scales[j];
var rsW = rW * scale;
var rsH = rH * scale;
var anchor = anchors.Row(i * numScale + j);
anchor[0] = cx - rsW * 0.5f;
anchor[1] = cy - rsH * 0.5f;
anchor[2] = cx + rsW * 0.5f;
anchor[3] = cy + rsH * 0.5f;
}
}
return(anchors);
}
private static void GenerateProposals(Mat anchors, int featStride, Mat scoreBlob, Mat bboxBlob, Mat landmarkBlob, float probThreshold, IList <FaceObject> faceObjects)
{
var w = scoreBlob.W;
var h = scoreBlob.H;
// generate face proposal from bbox deltas and shifted anchors
var numAnchors = anchors.H;
for (var q = 0; q < numAnchors; q++)
{
var anchor = anchors.Row(q);
using var score = scoreBlob.Channel(q + numAnchors);
using var bbox = bboxBlob.ChannelRange(q * 4, 4);
using var landmark = landmarkBlob.ChannelRange(q * 10, 10);
// shifted anchor
var anchorY = anchor[1];
var anchorW = anchor[2] - anchor[0];
var anchorH = anchor[3] - anchor[1];
for (var i = 0; i < h; i++)
{
var anchorX = anchor[0];
for (var j = 0; j < w; j++)
{
var index = i * w + j;
var prob = score[index];
if (prob >= probThreshold)
{
// apply center size
using var mat0 = bbox.Channel(0);
using var mat1 = bbox.Channel(1);
using var mat2 = bbox.Channel(2);
using var mat3 = bbox.Channel(3);
var dx = mat0[index];
var dy = mat1[index];
var dw = mat2[index];
var dh = mat3[index];
var cx = anchorX + anchorW * 0.5f;
var cy = anchorY + anchorH * 0.5f;
var pbCx = cx + anchorW * dx;
var pbCy = cy + anchorH * dy;
var pbW = anchorW * (float)Math.Exp(dw);
var pbH = anchorH * (float)Math.Exp(dh);
var x0 = pbCx - pbW * 0.5f;
var y0 = pbCy - pbH * 0.5f;
var x1 = pbCx + pbW * 0.5f;
var y1 = pbCy + pbH * 0.5f;
var obj = new FaceObject();
obj.Rect.X = x0;
obj.Rect.Y = y0;
obj.Rect.Width = x1 - x0 + 1;
obj.Rect.Height = y1 - y0 + 1;
using var landmarkMat0 = landmark.Channel(0);
using var landmarkMat1 = landmark.Channel(1);
using var landmarkMat2 = landmark.Channel(2);
using var landmarkMat3 = landmark.Channel(3);
using var landmarkMat4 = landmark.Channel(4);
using var landmarkMat5 = landmark.Channel(5);
using var landmarkMat6 = landmark.Channel(6);
using var landmarkMat7 = landmark.Channel(7);
using var landmarkMat8 = landmark.Channel(8);
using var landmarkMat9 = landmark.Channel(9);
obj.Landmark[0].X = cx + (anchorW + 1) * landmarkMat0[index];
obj.Landmark[0].Y = cy + (anchorH + 1) * landmarkMat1[index];
obj.Landmark[1].X = cx + (anchorW + 1) * landmarkMat2[index];
obj.Landmark[1].Y = cy + (anchorH + 1) * landmarkMat3[index];
obj.Landmark[2].X = cx + (anchorW + 1) * landmarkMat4[index];
obj.Landmark[2].Y = cy + (anchorH + 1) * landmarkMat5[index];
obj.Landmark[3].X = cx + (anchorW + 1) * landmarkMat6[index];
obj.Landmark[3].Y = cy + (anchorH + 1) * landmarkMat7[index];
obj.Landmark[4].X = cx + (anchorW + 1) * landmarkMat8[index];
obj.Landmark[4].Y = cy + (anchorH + 1) * landmarkMat9[index];
obj.Prob = prob;
faceObjects.Add(obj);
}
anchorX += featStride;
}
anchorY += featStride;
}
}
}
