您好，非常感謝您的工作 請問在運行train.m時出現錯誤該如何解決

[e04963852741]

不好意思 當我嘗試訓練時碰到以下錯誤
[1][6/6] BatchTime(s):0.93 , LR:0.00001, boxLoss:235.416 , objLoss:357.958 , clsLoss:0.000 , totalLoss:593.37390 , meanLoss:3704.30737
[1][7/6] BatchTime(s):0.47 , LR:0.00001, boxLoss:332.298 , objLoss:235.153 , clsLoss:0.000 , totalLoss:567.45081 , meanLoss:3259.88818
[2][1/6] BatchTime(s):1.04 , LR:0.50000, boxLoss:412.392 , objLoss:196.623 , clsLoss:0.000 , totalLoss:609.01556 , meanLoss:2923.33350
[2][2/6] BatchTime(s):0.88 , LR:0.50000, boxLoss:Inf , objLoss:71.741 , clsLoss:0.000 , totalLoss:Inf , meanLoss:2666.18701
[2][3/6] BatchTime(s):0.85 , LR:0.50000, boxLoss:459.970 , objLoss:70.744 , clsLoss:0.000 , totalLoss:530.71442 , meanLoss:Inf
Error using nnet.internal.cnn.dlnetwork/forward (line 254)
Layer 'bn_2': Invalid input data. The value of 'Variance' is invalid. Expected input to be positive.

Error in nnet.internal.cnn.dlnetwork/CodegenOptimizationStrategy/propagateWithFallback (line 103)
[varargout{1:nargout}] = fcn(net, X, layerIndices, layerOutputIndices);

Error in nnet.internal.cnn.dlnetwork/CodegenOptimizationStrategy/forward (line 52)
[varargout{1:nargout}] = propagateWithFallback(strategy, functionSlot, @forward, net, X, layerIndices, layerOutputIndices);

Error in dlnetwork/forward (line 347)
[varargout{1:nargout}] = net.EvaluationStrategy.forward(net.PrivateNetwork, x, layerIndices, layerOutputIndices);

Error in train>modelGradients (line 169)
[outFeatureMaps{:},state] = forward(net,XTrain,'Outputs',yolov3layerNames);

Error in deep.internal.dlfeval (line 18)
[varargout{1:nout}] = fun(x{:});

Error in dlfeval (line 41)
[varargout{1:nout}] = deep.internal.dlfeval(fun,varargin{:});

Error in train (line 119)
[gradients,boxLoss,objLoss,clsLoss,totalLoss,state] = dlfeval(@modelGradients, model, XTrain, YTrain,yoloLayerNumber);

非常感謝您的工作，請問這個問題該如何解決，希望能得到您的解答

[Hind-colla]

您好，您找到解決方案了嗎？我也有同樣的問題

[yangchengjian-bit]

您好，请问您解决这个问题了吗，我这两天也解决不了这个问题