Philipp Schmidt

Hi, a main source of wrong results and bad accuracy has been fixed for me in triton inference server. It was a server side race condition... I was hunting ghosts...

I couldn't yet make the time to fully tackle this as well unfortunately. This Polygraph tool seems to be very helpful regardless, thanks for the pointer.

Interesting results, thanks for checking it out jkjung. I'm curious if there are any guarantees from TensorRT regarding precision. And taking into account that TensorRT selects from a range of...

Same behavior here. Charts will not fit into parent container until the first update of their data. Any ideas? I tried loading the data "delayed" by loading them inside `useEffect()`,...

You don't have gpu support in your container then. Check available documentation on how to enable the nvidia runtime for docker.

Postprocessing has been fixed in v1.3.0. Initial results look very similar to default yolov4. Further testing is needed though.

Hi, the fix I used for v1.3.0 is not necessary in jkjungs implementation as he confirmed: https://github.com/jkjung-avt/tensorrt_demos/issues/315 I will have to implement mAP checks natively in C++ (directly with TensorRT...

Hi @shumwaymark, I recently implemented a multithreaded PUB/SUB subscriber as an example in imagezmq, which enables one-to-many broadcast with the receivers doing realtime (potentially heavy load) processing. It should work...

@WongKinYiu Hello WongKinYiu, I am using your repo to load darknet weights and export them into ".wts" format so I can parse and load them into TensorRT. Unfortunately I can...

Similar issue: https://github.com/tjuskyzhang/Scaled-YOLOv4-TensorRT/issues/5