trt-yolo-app compile error on Xavier

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi,

trt-yolo-app (https://github.com/vat-nvidia/deepstream-plugins) works well on P4 and Jetson TX2, but
when I compiled the trt-yolo-app on Xavier, a make error occurs:

trt_utils.h:83:22: error: ‘nvinfer1::DimsHW YoloTinyMaxpoolPaddingFormula::compute(nvinfer1::DimsHW, nvinfer1::DimsHW, nvinfer1::DimsHW, nvinfer1::DimsHW, nvinfer1::DimsHW, const char*)’ marked ‘override’, but does not override nvinfer1::DimsHW compute(nvinfer1::DimsHW inputDims, nvinfer1::DimsHW kernelSize,

Thanks.

2

Hi ywl22,

That’s not ready for Xavier yet.
We will have the specific version for Xavier in coming months, please stay tuned.

Thanks

3

Look forward to it. thx.

4

@ywl22 Xavier is currently using TensorRT 5 and the repo is supposed to be compiled with TensorRT 4. To compile the code on Xavier, you will need to make a change. Please follow the instructions in this comment upgrade to TensorRT 5. [url]https://devtalk.nvidia.com/default/topic/1043214/general/trt-for-yolov3-fp16-and-int8-optimization-failed/post/5293723/#5293723[/url]

5

Thx!