Leemengwei
Leemengwei
@zerollzeng Hi, want to know if specifying _computecapacity_ is supported when using trtexec convertion (from say, onnx)? It's really painful when I'm trying to migrate a trt model to another...
> same issue here > Update: using a different version works for me (DEFAULT_WECHAT_VERSION=2.9.0.114) Thankyou！
> hi In my case, it was a simple code error. Refactoring the code to find the problem. Could you explain more ? thanks in advance!
> Hello, it takes about 39 hours on 8xA100 for [DiffusionDet-COCO-Res50](https://github.com/ShoufaChen/DiffusionDet/blob/main/configs/diffdet.coco.res50.yaml). Hi may I know the inference time of each image? for example on 640x640x3 image
@ShoufaChen thanks4 reply Yet as metioned in paper: "The run time is evaluated on a single NVIDIA A100 GPU with a mini-batch size of 1" which achieves about 30fps .......
how to check them？ its worth mention that such error occurs by chance。 发自我的iPhone ------------------ Original ------------------ From: Herman Chen ***@***.***> Date: Fri,Dec 15,2023 2:02 PM To: rockchip-linux/mpp ***@***.***> Cc:...