how i can fix internal change in number of elements in yolo v4 network while training
39 次查看(过去 30 天)
显示 更早的评论
Error using reshape
Number of elements must not change. Use [] as one of the size inputs to automatically calculate the appropriate size for that dimension.
iou(:,:,:,batchSize) = reshape(maxOverlap,h,w,c);
iou = iGetMaxIOUPredictedWithGroundTruth(bx,by,bw,bh,groundTruth,isRotatedBox);
[boxTarget, objectnessTarget, classTarget, objectMaskTarget, boxErrorScale] = iGenerateTargets(gatheredPredictions, YTrain, params.InputSize, params.AnchorBoxes, penaltyThreshold, isRotatedBox);
Error in trainYOLOv4ObjectDetector>@(varargin)calculateLoss(lossParams,isRotatedBox,varargin) (line 226)
lossFcn = @(varargin) calculateLoss(lossParams,isRotatedBox,varargin);
loss = lossFcn(networkOutputs{:},targets{:});
[varargout{1:nargout}] = fun(x{:});
[varargout{1:nargout}] = deep.internal.dlfeval(fun,varargin{:});
[varargout{1:nargout}] = deep.internal.dlfevalWithNestingCheck(fun,varargin{:});
[loss,grad,state,networkOutputs,lossData] = dlfeval(@modelGradients,self.Network,self.LossFcn,...
net = fit(networkTrainer);
[trainedDetector,infoTrain] = images.dltrain.internal.dltrain(mbq,detector,options,lossFcn,metrics,validationPatienceMetric,'ExperimentMonitor',params.ExperimentMonitor);
I have single class dataset withy class name person and this is error i am facing a time of training, i have gpu compute capacity 5.2 with gpu Nvidia M400
what could be issue here , i am cofuse that is it with preprocessing or compute capacity
3 个评论
Joss Knight
2024-8-19,21:22
Maaz, what is your training data and responses? My guess is that your training targets do not match the data. You will need to provide more code.
回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Computer Vision Toolbox 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!