tensorrtx

tensorrtx copied to clipboard

issues about the size of yolov5s-int8 and yolov5s-fp16

4

## Env - GPU, e.g. V100, RTX2080, TX2, Xavier NX, Nano, etc. - OS, e.g. Ubuntu16.04, Win10, etc. - Cuda version - TensorRT version ## About this repo - which...

JackjackFan

Hello everyone, I'm using the yolov5 directory of this project and I'm trying to take only the necessary parts of it and put it into a ROS node. Right now...

EmiliyanGospodinov

semantic-segmentation build error

3

[100%] Linking CXX executable swintransformer /usr/bin/ld: CMakeFiles/swintransformer.dir/UpsamplePlugin.cpp.o: in function `UpsamplePlugin::enqueue(int, void const* const*, void* const*, void*, CUstream_st*)': UpsamplePlugin.cpp:(.text+0x1a4): undefined reference to `UpsampleInference(CUstream_st*, int, int, int, int, int, float, float, void...

avBuffer

make error CMakeFiles/yolov5.dir/build.make:147: recipe for target 'yolov5' failed

3

[100%] Linking CXX executable yolov5 /usr/bin/ld: warning: libnvrtc.so.10.2, needed by /home/zy/download/TensorRT-7.2.2.3/lib/libnvinfer.so, not found (try using -rpath or -rpath-link) /usr/bin/ld: warning: libcublas.so.10, needed by /home/zy/download/TensorRT-7.2.2.3/lib/libmyelin.so.1, not found (try using -rpath or...

W8ming

Yolov5s' INT8 model gave very poor result.

1

## Env - GPU Nvidia AGX Xavier - OS, Ubuntu18.04 - Cuda version 10.2 - TensorRT 7.1.3 ## About this repo - tag: v5.0 - model: yolov5 ## Your problem...

yijliu7

It don't work with yolov5-6.0

1

## Env - GPU, GTX1060 - OS, Win10 - Cuda version, 10.2 - TensorRT version, TensorRT-7.0.0.11_cuda10.2 ## About this repo - which branch/tag/commit are you using? master - which model?...

Wangwang99999

./detr -s ../detr.wts detr.engine error

1

Cuda11.4 TensorRT8.4.0 model: detr-r50-e632da11.pth [06/14/2022-16:09:31] [E] [TRT] 4: (Unnamed Layer* 186) [Matrix Multiply]: last dimension of input0 = 850 and last dimension of input1 = 32 but must match. Your...

avBuffer

Tensorrt doInference一帧推理时间不稳定

2

请教大佬，如题，是单GPU显卡， doInference一帧推理的时候有时是40ms, 有时候是150ms,有时候是80ms, 一般是什么原因？

zhuimeng2080

for (int i = 0; i < 70*batch_num ; i++) { int maxj = 0; for (int j = 1; j < 7607; j++) { if (prob[(7607 * i +...

pureloveljc

tensorrtx/yolov5/yololayer.h:6:10: fatal error: NvInfer.h: 没有那个文件或目录

4

 Excuse me, how to solve this problem？

dailonggang