Chen Xin comments

Results 250 comments of


                                            Chen Xin

python object_detection.py inference .engine error

From the above information, I don't konw how to reproduce your problem. Please describe how to reproduce the python problem in detail or you can add our wechat group and...

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

It seems like the cuda version in your C drive is different from the cudatoolkit that pytorch built with. (I guess it is cuda11.0. If so, please install cuda11.1 instead...

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

The visualize error is a known issue. It seems that there is a conflict when use pytorch and tensorrt simultaneously. While if you use C api to do the inference,...

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

Can you paste your system path. If you use powershell, you can print the variable with ``` echo $Env:PATH ```

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

Could you please try to use tensorrt-8.2.3.0 and cudnn8.2.1? You may need reconvert the model.

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

![image](https://user-images.githubusercontent.com/16019484/178914996-493b03ca-e25b-4828-b751-0b96b95c0143.png) You should reconvert the model since the old model is converted under tensorrt8.2.1

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

The 'same problem' refer to what? The 'engine plan file is not compatible with this version of TensorRT' or your original 'Myelin( compiled against cudnn11.3.0.0 but running against cudnn 11.2.1.0)'?

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

Sorry, it is my fault. I didn't see clearly. What the error means is that the engine file is converted under 8.2.1 but the runtime library that found is 8.2.3.

[mmdeploy] [error] [trt_net.cpp:28] TRTNet: 3: [executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924] Error Code 3: API Usage Error (Parameter check failed at: executionContext.cpp::nvinfer1::rt::ExecutionContext::setBindingDimensions::924, condition: mOptimizationProfile >= 0 && mOptimizationProfile < mEngine.getNbOptimizationProfiles()

What confuses you are two things. 1. When convert the model, why the log say that it load cudnn8.0.5 other than 8.2.1 in your path? A: When you install pytorch,...

ERROR with no trace back.

Currently, the convert process has some issues on windows (some people can't convert on windows, we haven't figure it out). For now, you can convert the model on linux and...