Frequently Asked Questions¶
No C++17 Compiler(Linux)?¶
aptas your package manager?
Helpful link: LINK.
Build a C++17 compiler from source.
Build without examples/tests?¶
cmake .. -DBUILD_EXAMPLES=OFF -DBUILD_TESTS=OFF
Build OpenCV from source?¶
Refer to here.
Network problem when installing the test models/data from the command line?¶
Download them manually:
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 outputwhen using the
TinyVGG-V1-HW=256x384.uffmodel. 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)