Seungtaek Kim

I tested [ljn917:cppflow2-fix-context](https://github.com/ljn917/cppflow/tree/cppflow2-fix-context) branch with this [code](https://gist.github.com/seungtaek94/59bb4bfc76efdc8fa8710cddbc30e378). And it works. But can we handle to use different context with different object like below? Now it seems like cant handle. ```c++...

[ljn917:cppflow2-fix-context2](https://github.com/ljn917/cppflow/tree/cppflow2-fix-context2) this branch also works. I tested both branch with win10, rtx 2080 super * 2. > @seungtaek94 Can you also test this [branch](https://github.com/ljn917/cppflow/tree/cppflow2-fix-context2) for me? The differences are in...

@ljn917 Thanks for information. So for my case, I need to set global context with all GPU(two gpus) and then set device for each graph. Am i correct?

Thanks. Anyway, both branch those you mentioned, it works :)

@Innan666 , @haryngod in windows system has problem at that parts. so u should change that [cord](https://github.com/xingyizhou/CenterNet/blob/master/src/lib/models/networks/pose_dla_dcn.py#L22) or download directly. u can change that part like below; ```python url =...

https://github.com/enazoe/yolo-tensorrt/issues/51#issuecomment-917840303 I also have issue in cuda 11.3 and tensorrt 8 :(

> @seungtaek94 past the error log, I have test the trt8 branch code on windows (vs2017 cuda10.1 trt8.0.1.6 gtx1080ti) everything is all right. What should value that `_n_size_split` be ?...

Sorry for late response. I didnt change anything in code. I chaged only `*.cfg` and `*.weights` path for each model. Actually, I tested `yolov4-csp.cfg`, `yolov4-tiny.cfg` and `yolob5s`. Only `yolov4-tiny.cfg` didn't...

i met same problem when i trained my own dateaset. my hm_val_loss also stop at 9.208 :( 

Only binary file doesn't work with the GPU. The other method that `.python ./anylabeling./app.py` work with the GPU. I tried below method to run binary file with the GPU. I...