Ghustwb / MobileNet-SSD-TensorRT

Accelerate mobileNet-ssd with tensorRT
188 stars 91 forks source link

I can not run this code #2

Closed coolzhangfeng closed 5 years ago

coolzhangfeng commented 5 years ago

it compiled suc,but it can not run,the error is mobileNetSSDTensorRT: NvPluginSSD.cu:795: virtual void nvinfer1::plugin::DetectionOutput::configure(const nvinfer1::Dims, int, const nvinfer1::Dims, int, int): Assertion `numPriorsnumLocClasses4 == inputDims[param.inputOrder[0]].d[0]' failed. 已放弃 (核心已转储) can you tell me why?thanks very much

Ghustwb commented 5 years ago

If you use TensorRT4 You should modify some code in pluginImplement.cpp uncomment line 525,comment line 524 uncomment line 533,534,535

coolzhangfeng commented 5 years ago

If you use TensorRT4 You should modify some code in pluginImplement.cpp uncomment line 525,comment line 524 uncomment line 533,534,535

wawa,it has worked, I will read the code carefully.Do you have this development document for your project?It's hard to understand your idea by looking at code. I have use tensorrt with pytorch and onnx,It's much simpler than your code. We can talk more about tensor RT.