tensorRT5 INT8 SSD failed

AI & Data Science Deep Learning (Training & Inference) TensorRT
1

hi, I have a problem with errors as below:
ERROR: engine.cpp (404) - Cuda Error in commonEmitTensor: 11
ERROR: Failure while trying to emit debug blob.
engine.cpp (404) - Cuda Error in commonEmitTensor: 11
ERROR: cuda/customWinogradConvActLayer.cpp (319) - Cuda Error in execute: 11
ERROR: cuda/customWinogradConvActLayer.cpp (319) - Cuda Error in execute: 11

engine.cpp (404) - Cuda Error in commonEmitTensor: 11
ERROR: cuda/customWinogradConvActLayer.cpp (319) - Cuda Error in execute: 11
ERROR: cuda/customWinogradConvActLayer.cpp (319) - Cuda Error in execute: 11
ERROR: runtime.cpp (30) - Cuda Error in free: 77
terminate called after throwing an instance of ‘nvinfer1::CudaError’

2

Hello,

cudaErrorInvalidValue = 11
This indicates that one or more of the parameters passed to the API call is not within an acceptable range of values.

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

Please share how you are arriving at this error?

3

I have solved this problem, because there is something wrong when generate the batches.

I have meet a new problem, when INT8 calibration using entropy calibrator, 'calibrator.reset(new Int8EntropyCalibrator(calibrationStream, kFIRST_CAL_BATCH)) ', but do not run member function ‘updata()’ of class ‘BatchStream’.

ubuntu14.04
GPU:p40
driver: 410.79
cuda-10.0
cudnn-7.3
tensorRT-5.0.2.6

4

Hi,

I am having the exact same problem. Can you tell me how exactly did you fix it? What was wrong with your batch generation?