Frequently Asked Questions


No C++17 Compiler(Linux)?

  • Using apt as your package manager?

    • Install from ppa.

    • Helpful link: LINK.

  • Otherwise

    • Build a C++17 compiler from source.

Build without examples/tests?


Build OpenCV from source?

Refer to here.

Network problem when installing the test models/data from the command line?

Download them manually:



TensorRT Error?

  • See the tensorrt.log. (it contains more informations about logging and is located in where you execute the binary)

  • You may meet ERROR: Tensor image cannot be both input and output when using the hao28-600000-256x384.uff model. And just ignore it.


  • Usually the 1st try of execution(cold start) on small amount of data tends to be slow. You can use a longer video/more images to test the performance(or run it more than once).

  • The performance is mainly related to the followings(you can customize the followings):

    • The complexity of model(not only FLOPS but also parameter numbers): smaller is usually better.

    • The model network resolution(alse see here): smaller is better.

    • Batch size: bigger is faster(higher throughput). (For details, you can refer to Shen’s dissertation)

    • The input / output size(this mainly involves in the speed of cv::resize): smaller is better.

    • The upsampling factor of the feature map when doing post processing: smaller is better. (By default the PAF parser will upsample the feature map by 4x. We did this according to the Lightweight-OpenPose paper.)

  • Use better hardware(Good CPUs can make the post-processing faster!).

  • Use SIMD instructions of your CPU. (Compile OpenCV from source and enable the instruction sets in cmake configuration)