Problem converting customised trained ssd mobilenet v2 uff to engine format -TENSORRT

python3: nmsPlugin.cpp:139: virtual void nvinfer1::plugin::DetectionOutput::configureWithFormat(const nvinfer1::Dims*, int, const nvinfer1::Dims*, int, nvinfer1::DataType, nvinfer1::PluginFormat, int): Assertion `numPriors * numLocClasses * 4 == inputDims[param.inputOrder[0]].d[0]’ failed.
Aborted (core dumped)

Hi,

Facing above error while converting Problem converting customised trained ssd mobilenet v2 uff to engine format

Anyone help!!

I was able to convert ssd_mobilenet_v2 to tensort

The solution to above problem is
If Custom model trained with one class then give
numClasses=2 (one is your class and the other class is background class)

inputOrder=[0,2,1]

Put these two parameters in your config file and you will be able to convert succesfully

Hope this helps someone else!!

Thanks Ambika. This really worked for me.

Thanks! It worked for me too.