When I am running command it’s giving me error for INT8
python3 tensorrt.py --frozen_graph=resnetv2_imagenet_frozen_graph.pb --image_file=image.jpg --native --fp32 --fp16 --int8 --output_dir=output_trt
nvinfer1::getCHW(const nvinfer1::Dims&): Assertion `d.nbDims >= 3’ failed
(Using Tesla V100, Ubuntu, No custom code, Cuda version : 9.2, Tensorrt4)