tensorRT for yolo v3 int8 optimization failed ?

I build a network with Network Definition API,and generate kFLOAT engine successful, and images detection result is right. But with the API “builder->setInt8Mode(true); builder->setInt8Calibrator(calibrator);”, I generate kInt8 engine failed, with this error:"…/builder/cudnnBuilder2.cpp:685: virtual std::vector<nvinfer1::query::Portsnvinfer1::query::TensorRequirements > nvinfer1::builder::Node::getSupportedFormats(const nvinfer1::query::Portsnvinfer1::query::AbstractTensor&, const nvinfer1::cudnn::HardwareContext&, nvinfer1::builder::Format::Type, const nvinfer1::builder::FormatTypeHack&) const: Assertion `sf’ failed.
Aborted (core dumped)".

Facing the same problem here.
I really love this kind of esoteric error messages…
What does it mean?


Hello, can you provide details on the platforms you are using?

Linux distro and version
GPU type
nvidia driver version
CUDA version
CUDNN version
Python version [if using python]
Tensorflow version
TensorRT version

It’d help us debug if you can provide a small repro package containing the source, model, dataset (if applicable) that exhibit the symptoms you are seeing.