Yanlin Qiu

Yes, customized models are supported by libtorch. Actually, you could build any model since it has same interface as python version, e.g. I just migrated YOLO v3 in cpp api:...

Hi Alex, I have not tested yet, but high CPU usage might be caused by function 'write_results', since a few lines of code in this method is running on CPU....

@Alex18947 , thanks for your information. I will do some testing on the CPU consumption later and let you know if I get something new.

检查CUDA 是否可用： ``` if (torch::cuda::is_available() ) { // CUDA 是否可用 } ``` 另外，最新代码适配了 libtorch 1.3。

根据报错日志自己调试下

font{ line-height: 1.6; } ul,ol{ padding-left: 20px; list-style-position: inside; } for (int i = 0; i < result.size(0) ; i++) {  // left x, left y, right x, right y,...

https://github.com/walktree/libtorch-yolov3/issues/12 https://github.com/walktree/libtorch-yolov3/issues/4

#12 #4

I did not test on CPU, thanks @zacario-li

Not sure how you guys test, but I got 25 ms on GPU ( 1080ti ). There is a comment in the code: "It should be known that it takes...