enazoe

Results 84 comments of enazoe

@tuteming 如果你用cmake来构建的话,现在的cmake文件只能作为参考,可能要修改,dll的生成需要除了sample下的文件剩下的所有文件,如果你现在编译ok,run出错不一定是成像问题,可能是路径问题,比如说图片路径,模型路径之类的

What is the batchsize and the model width and height?

https://github.com/enazoe/yolo-tensorrt/issues/99#issuecomment-767974798

you push 16 images at same time and get the inference time is 20ms per image? And you should note yolov5 is daynamic inpute.

bacause the gpu compute capabilities is already saturated when the batch is 1

@xpeedster @freeluojing123 check the version of cuda trt cudnn

try update the jetpack to 4.4