Wrong prediction when running caffe_demo for ssdlite using coco dataset

[balajib363]

Awesome idea of execution. After following all the steps, when i execute the demo_caffe.py project, facing below issue I0530 12:31:54.303753 14700 layer_factory.hpp:77] Creating layer Conv/relu F0530 12:31:54.303789 14700 layer_factory.hpp:81] Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type: ReLU6 (known types: AbsVal, Accuracy, AnnotatedData, ArgMax, BNLL, BatchNorm, BatchReindex, Bias, Concat, ContrastiveLoss, Convolution, Crop, Data, Deconvolution, DetectionEvaluate, DetectionOutput, Dropout, DummyData, ELU, Eltwise, Embed, EuclideanLoss, Exp, Filter, Flatten, HDF5Data, HDF5Output, HingeLoss, Im2col, ImageData, InfogainLoss, InnerProduct, Input, LRN, LSTM, LSTMUnit, Log, MVN, MemoryData, MultiBoxLoss, MultinomialLogisticLoss, Normalize, PReLU, Parameter, Permute, Pooling, Power, PriorBox, RNN, ReLU, Reduction, Reshape, SPP, Scale, Sigmoid, SigmoidCrossEntropyLoss, Silence, Slice, SmoothL1Loss, Softmax, SoftmaxWithLoss, Split, TanH, Threshold, Tile, VideoData, WindowData) Check failure stack trace: Aborted (core dumped)

[gerynasa]

Add ReLU6, then the accuracy will be btter than ReLU