函数[Bboxes，Scores，LabelsIndex] = Yolov3Detect（Matfile，IM，... NetworkInputSize，NetworkOutputs，ConcidenceThreshold，...重叠，类）％Yolov3Detect函数检测图像中的边界框，分数和％LabelSindex。％＃codegen％copyright 2020-2021 Mathworks，Inc. %%预处理数据％此示例将所有预处理变换应用于在培训期间应用的数据集中的数据集，但数据增强除外。由于示例性％使用预先磨碎的YOLO V3网络，因此输入数据必须是原始数据的代表性％，并且未经修改以进行无偏的评估。％特别是以下预处理操作应用于％输入数据。％1.将图像调整为网络输入大小，因为图像比NetworkInputSize大。2.缩放范围[0 1]的图像像素。3.将调整大小和重新定义的图像转换为Dlarray对象。IM = DLARRAY（PreprocessData（IM，NetworkInputSize），“SSCB”）;图像=尺寸（IM，[1,2]）;%%定义锚框％指定基于培训YOLO V3网络时使用的预处理％训练数据估计的锚盒。 These anchor box % values are same as mentioned in "Object Detection Using YOLO v3 Deep % Learning" example. For details on estimating anchor boxes, see "Anchor % Boxes for Object Detection". anchors = [ 41 34; 163 130; 98 93; 144 125; 33 24; 69 66]; % Specify anchorBoxMasks to select anchor boxes to use in both the % detection heads of the YOLO v3 network. anchorBoxMasks is a cell array of % size M-by-1, where M denotes the number of detection heads. Each % detection head consists of a 1-by-N array of row index of anchors in % anchorBoxes, where N is the number of anchor boxes to use. Select anchor % boxes for each detection head based on size-use larger anchor boxes at % lower scale and smaller anchor boxes at higher scale. To do so, sort the % anchor boxes with the larger anchor boxes first and assign the first % three to the first detection head and the next three to the second % detection head. area = anchors(:, 1).*anchors(:, 2); [~, idx] = sort(area, 'descend'); anchors = anchors(idx, :); anchorBoxMasks = {[1,2,3],[4,5,6]}; %% Predict on Yolov3 % Predict and filter the detections based on confidence threshold. predictions = yolov3Predict(matFile,im,networkOutputs,anchorBoxMasks); %% Generate Detections % indices corresponding to x,y,w,h predictions for bounding boxes anchorIndex = 2:5; tiledAnchors = generateTiledAnchors(predictions,anchors,anchorBoxMasks,... anchorIndex); predictions = applyAnchorBoxOffsets(tiledAnchors, predictions,... networkInputSize, anchorIndex); [bboxes,scores,labelsIndex] = generateYOLOv3DetectionsForCodegen(predictions,... confidenceThreshold, overlapThreshold, imageSize, classes); end function YPredCell = yolov3Predict(matFile,im,networkOutputs,anchorBoxMask) % Predict the output of network and extract the confidence, x, y, % width, height, and class. % load the deep learning network for prediction persistent net; if isempty(net) net = coder.loadDeepLearningNetwork(matFile); end YPredictions = cell(coder.const(networkOutputs), 1); [YPredictions{:}] = predict(net, im); YPredCell = extractPredictions(YPredictions, anchorBoxMask); % Apply activation to the predicted cell array. YPredCell = applyActivations(YPredCell); end

代码生成成功：查看报告

函数ypredcell = applyactivations（ypredcell）％＃codegen％copyright 2020-2021 Mathworks，Inc. numcells = size（ypredcell，1）;对于ICELL = 1：Numcell用于IDX = 1：3 YPRedCell {icell，Idx} = SigMoidactivation（YpredCell {icell，Idx}）;icell终端= 1：numcell for idx = 4：5 ypredcell {icell，idx} = exp（ypredcell {icell，idx}）;iCell末端= 1：Numcells Ypredcell {icell，6} =唾液变性（Ypredcell {icell，6}）;结束功能OUT = SigMoidactivation（x）Out = 1./ (1 + exp（毒奏））;结束

函数预测= extractPredictions（YPredictions，anchorBoxMask）％＃代码生成％版权所有2020年至2021年MathWorks公司numPredictionHeads =尺寸（YPredictions，1）;预测=细胞（numPredictionHeads，6）;为II = 1：numPredictionHeads％获取有关特征尺寸所需要的信息。numChannelsPred =尺寸（YPredictions {二}，3）;numAnchors =尺寸（anchorBoxMask {II}，2）;numPredElemsPerAnchors = numChannelsPred / numAnchors;allIds =（1：numChannelsPred）;跨度= numPredElemsPerAnchors;endIdx = numChannelsPred;YPredictionsData = ExtractData由（YPredictions {II}）; % X positions. startIdx = 1; predictions{ii,2} = YPredictionsData(:,:,startIdx:stride:endIdx,:); xIds = startIdx:stride:endIdx; % Y positions. startIdx = 2; predictions{ii,3} = YPredictionsData(:,:,startIdx:stride:endIdx,:); yIds = startIdx:stride:endIdx; % Width. startIdx = 3; predictions{ii,4} = YPredictionsData(:,:,startIdx:stride:endIdx,:); wIds = startIdx:stride:endIdx; % Height. startIdx = 4; predictions{ii,5} = YPredictionsData(:,:,startIdx:stride:endIdx,:); hIds = startIdx:stride:endIdx; % Confidence scores. startIdx = 5; predictions{ii,1} = YPredictionsData(:,:,startIdx:stride:endIdx,:); confIds = startIdx:stride:endIdx; % Accumulate all the non-class indexes nonClassIds = [xIds yIds wIds hIds confIds]; % Class probabilities. % Get the indexes which do not belong to the nonClassIds classIdx = setdiff(allIds, nonClassIds, 'stable'); predictions{ii,6} = YPredictionsData(:,:,classIdx,:); end end

函数tiledanchors = generateTiledanchors（ypredcell，anchorboxes，... anchorboxmask，anchorIndex）％生成瓷砖锚偏移，用于将预测转换为从yolo％V3网格单元坐标转换为边界框坐标％＃codegen％2020-2021 MathWorks，Inc。numpredictionheads = size（ypredcell，1）;Tiledanchors = Cell（NumPredictionHeads，尺寸（锚定指示，2））;对于i = 1：numpredictionheads anchors =锚箱（anchorboxmask {i}，:);[h，w，〜，n] =大小（ypredcell {i，1}）;[Tiledanchors {i，2}，倾斜者{i，1}] = ndgrid（0：h-1,0：w-1，... 1：尺寸（锚，1），1：n）;[〜，〜，Tiledanchors {i，3}] = ndgrid（0：h-1,0：w-1，锚（:,2），1：n）;[〜，〜，Tiledanchors {i，4}] = ndgrid（0：h-1,0：w-1，锚（：，1），1：n）;结束

函数ypredcell = applyanchorboxoffsets（tiledanchors，ypredcell，... InputImagesize，anchorIndex）％＃codegen％从yolo v3网格小区的预测转换为％边界框坐标％2020-2021 Mathworks，Inc。对于i = 1：尺寸（ypredcell，1）[h，w，〜，〜] =大小（ypredcell {i，1}）;ypredcell {i，anchorIndex（1）} =（蒂尔美女{i，1} + ... ypredcell {i，anchorindex（1）}）./ w;ypredcell {i，anchorIndex（2）} =（蒂尔美女{i，2} + ... ypredcell {i，anchorindex（2）}）./ h;ypredcell {i，anchorIndex（3）} =（蒂尔美女{i，3}。* ... ypredcell {i，anchorIndex（3）}）./ InputImagesize（2）;ypredcell {i，anchorIndex（4）} =（蒂尔美女{i，4}。* ... ypredcell {i，anchorindex（4）}）./ingimagesize（1）;结束

函数映像=预处理数据（图像，targetsize）％调整图像大小并将像素缩放到0到1.％＃codegen％copyright 2020-2021 mathworks，Inc.Inmgsize = size（图像）;％使用单通道转换输入图像到3个通道。如果numel（Imgsize）<1图像= Repmat（图像，1,1,3）;结束图像= IM2Single（Rescale（图像））;image = iLetterBoxImage（图像，编码器.Const（targetsize（1：2）））;End函数Inew = iLetterBoxImage（I，Targencsize）％LeterBoxImage通过保留输入图像I的宽度和高度％宽高比来返回调整大小的图像。“TargetSize”是一个由目标维度的1×2向量组成的1.Y×2矢量。%%输入I可以是UINT8，UINT16，INT16，DOUBLE，SINGLE或LOGICAL，并且必须％是真实的和非稀疏。[ICOL，ICOL，ICH通道] =尺寸（i）;％计算宽高比。ARI = IROW./ICOL; % Preserve the maximum dimension based on the aspect ratio. if arI<1 IcolFin = targetSize(1,2); IrowFin = floor(IcolFin.*arI); else IrowFin = targetSize(1,1); IcolFin = floor(IrowFin./arI); end % Resize the input image. Itmp = imresize(I,[IrowFin,IcolFin]); % Initialize Inew with gray values. Inew = ones([targetSize,Ichannels],'like',I).*0.5; % Compute the offset. if arI<1 buff = targetSize(1,1)-IrowFin; else buff = targetSize(1,2)-IcolFin; end % Place the resized image on the canvas image. if (buff==0) Inew = Itmp; else buffVal = floor(buff/2); if arI<1 Inew(buffVal:buffVal+IrowFin-1,:,:) = Itmp; else Inew(:,buffVal:buffVal+IcolFin-1,:) = Itmp; end end end