Question

caffe报错：OpenCV Error: Assertion failed (blobs[0].num() == outCn && blobs[0].channels()

罗昀老师第五课作业，跑了一下第六课她给的代码，看起来training是成功的，但是test的时候出问题了，
我是用之前mnist那个例子的test方法，下面是我的test指令
g++ -o test_mnist test_mnist.cpp -lOpenCV_dnn -lopencv_highgui -lopencv_imgcodecs -lopencv_imgproc -lstdc++ -lopencv_core

就是吧之前的test_mnist.cpp改一下文件地址，我感觉理论没有太大问题，但是最后还是报错

OpenCV Error: Assertion failed (blobs[0].num() == outCn && blobs[0].channels() == inpCn / group) in allocate, file /home/Documents/OpenCV/opencv_contrib/modules/dnn/src/layers/convolution_layer.cpp, line 87
terminate called after throwing an instance of 'cv::Exception'
what(): /home/Documents/OpenCV/opencv_contrib/modules/dnn/src/layers/convolution_layer.cpp:87: error: (-215) blobs[0].num() == outCn && blobs[0].channels() == inpCn / group in function allocate

Aborted (core dumped)

卡在这里很久了，今天为了这个问题一直在搞，但是就是没有搞明白，希望好心人帮助一下，caffe弱渣在线求助！！

Answer 1

何Caffe配置每层结构近刚电脑装Caffe由于神经中国络同层结构同类型层同参数所根据Caffe官中国说明文档做简单总结1.VisionLayers1.1卷积层(Convolution)类型：CONVOLUTION例layers{name:"conv1"type:CONVOLUTIONbottom:"data"top:"conv1"blobs_lr:1#learningratemultiplierforthefiltersblobs_lr:2#learningratemultiplierforthebiasesweight_decay:1#weightdecaymultiplierforthefiltersweight_decay:0#weightdecaymultiplierforthebiasesconvolution_param{num_output:96#learn96filterskernel_size:11#eachfilteris11x11stride:4#step4pixelsbetweeneachfilterapplicationweight_filler{type:"gaussian"#initializethefiltersfromaGaussianstd:0.01#distributionwithstdev0.01(defaultmean:0)}bias_filler{type:"constant"#initializethebiasestozero(0)value:0}}}blobs_lr:习率调整参数面例设置权重习率运行求解器给习率同偏置习率权重两倍
用符号：m表示，我们走两步的距离约是 米，

Answer 2

e on Novembe