tensorrtx icon indicating copy to clipboard operation
tensorrtx copied to clipboard

Implementation of popular deep learning networks with TensorRT network definition API

Results 144 tensorrtx issues
Sort by recently updated
recently updated
newest added

Kernel affine transformation results are inconsistent with OpencV affine transformation results, how to modify?

When I run the yolov5_trt.py file in the windows environment, the following error occurs, how can I solve it? ![image](https://user-images.githubusercontent.com/44689801/173294993-5147673e-bdc8-4f54-b03a-f0eadeb29ef4.png)

## Env - Xavier NX - Ubuntu18.04 - Cuda version:10.2 - TensorRT version:8.2.1 ## About this repo yolov5 ## Your problem 我在jetson NX 编译yolov5,没有修改这个cmakelist.txt的内容,也可以编译成功,这是为什么呢? ![image](https://user-images.githubusercontent.com/47774299/191883081-eb60458e-a350-431f-89eb-274a6971f566.png)

您好,请教一下。 在yolov5.cpp中,这里的 &prob[b * OUTPUT_SIZE] 应该是prob数组中某一个元素的地址,在common.hpp中,output应该是&prob[b * OUTPUT_SIZE]的指针变量,但是在下面代码为什么有取output下标的操作呢? ![image](https://user-images.githubusercontent.com/47774299/189154229-6e6a6de4-9b6c-4ea4-bc08-8ea2671719fc.png) ![image](https://user-images.githubusercontent.com/47774299/189153295-c4747f34-8bcb-4f09-8ebc-b1bcda4724ea.png)

There is conv1d in my pytorch model. When converting to tensorRT, how to use the tensorRT API to define the conv1d layer?

## Env - GPU: 1080Ti - OS: Ubunut 18.04 - Cuda version: 11.4 - TensorRT version: 8.2.0.6 ## About this repo - which branch/tag/commit are you using? tensorrtx retinaface -...

## Env - GPU, RTX3090 - OS, Ubuntu 20.04 - Cuda, 11.3 - TensorRT version, TensorRT-8.0.1.6 - which branch/tag/commit are you using? yolov5-5.0 - which model? yolov5, retinaface? yolov5s download...

## Env - GPU, Nano - OS, - Cuda version 10.2 - TensorRT version ## About this repo repvgg ## Your problem sudo ./repvgg -s RepVGG-B2 // serialize model to...

## Env - GPU, Xavier ORIN - OS, Ubuntu20.04 - Cuda version 11.4 - TensorRT version 8.4 ## About this repo - which branch/tag/commit are you using? yolov5-v5.0 - which...

## Env - GPU, e.Xavier NX - OS, e.g. Ubuntu18.04 - Cuda version: 10.2.89 - TensorRT version: I am using a M-LSD model https://github.com/navervision/mlsd Since the M-LSD model is not...