enazoe / yolo-tensorrt

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.
MIT License
1.19k stars 316 forks source link

How to modify the batch size #95

Open NuBot-Cc opened 3 years ago

NuBot-Cc commented 3 years ago

Hi~ Thank you for your wonderful works!

When I convert YOLOv4-tiny to TensorRT, I get this error

yolo-trt: /home/nvidia/yolo-tensorrt/modules/yolo.cpp:925: void Yolo::doInference(const unsigned char*, uint32_t): AssertionbatchSize <= m_BatchSize && "Image batch size exceeds TRT engines batch size"' failed. ` Which document I need to modify the batch size in?

enazoe commented 3 years ago

At your cfg file