I am trying to run TensorRT over a detection model which contains batchnorm layers.
There shows an error information when load the caffemodel:
Message type "diccaffe.BatchNormParameter" has no filed name "scale_filler", could not parse deploy file.
After I delete the batch_norm_param filed in the deploy file, it shows another error info:
caffeParser.cpp:613: bool bnConvert(const nvinfer1::Weights&, const nvinfer1::Weights&, const nvinfer1::Weights&, float, nvinfer1::Weights&, nvinfer1::Weights&, std::vector<void*>&) [with T = float]: Assertion `mean.count == variance.count && movingAverage.count == 1' failed.