Deep-Learning-Accelerator-SW icon indicating copy to clipboard operation
Deep-Learning-Accelerator-SW copied to clipboard

Error when calibrating generated model using calibration cache file for tensorrt 10.3.0

Open trathpai opened this issue 1 year ago • 0 comments

I am trying to convert onnx model to tensorrt egnine. I am using trtexec utility for doing this. Engine file should run in int8 so i generated a calibration file using qdqtranslator . But when using the calibration file to convert to int8 , trtexec fails with error

[E] Error[3]: IExecutionContext::executeV2: Error Code 3: API Usage Error (Parameter check failed, condition: nullPtrAllowed. Tensor “input” is bound to nullptr, which is allowed only for an empty input tensor, shape tensor, or an output tensor associated with an IOuputAllocator.)

What could be causing this ? Is calibration file compatible with tensorrt 10.3.0 ?

Header of cache file looks like this

TRT-8600-EntropyCalibration2 input: 3d23ac36 /init_block/pool/MaxPool_output_0: 3e5b2be4 /stage1/unit1/body/conv1/activ/Relu_output_0: 3e540b45

trathpai avatar Oct 09 '24 13:10 trathpai