tensorrtx
tensorrtx copied to clipboard
Implementation of popular deep learning networks with TensorRT network definition API
windows VS2019 cuda11.3 cudnn 8,2 tensorrt 8.2.4 编译的时候,报错,可能是tensorrt8.2.4兼容问题,每个.cu文件编译的时候,里面的 new xxx 报错: 比如:fillmask.cu xxx\fillmask.cu(112): error : object of abstract class type "nvinfer1::fillmask" is not allowed: 1> pure virtual function "nvinfer1::IPluginV2::enqueue" has...
## Env - GPU T4. - OS Ubuntu18.04. - Cuda 10.2 - TensorRT version 7.0 ## About this repo - which branch/tag/commit are you using? - which model? retinaface ##...
请问如果想使用pytorch版本arcface,应该要做出一些什么改动呢?我使用resnet网络的方法提取的.wts,但是在生成引擎的时候导入.wts文件失败了
如题,我对yolov5的backbone进行了更换,如果向生成基于这个模型的engine文件应该对tensorrtx的哪部分进行调整?
I'm attempting to get the DETR model working on TensorRT 8. I've added the same macros for TRT8 on YOLOv5, YOLOv3, etc. and updated the deprecated signature call for `addMatrixMultiply`....
I and the addBatchedNMSLayer, when buildEngineWithConfig, it broke: when addBatchedNMSLayer function: IPluginV2Layer* addBatchedNMSLayer(INetworkDefinition* network, IPluginV2Layer* yolo, int num_classes, int top_k, int keep_top_k, float score_thresh, float iou_thresh, bool is_normalized = false,...
## Env - GPU RTX2080ti - OS - Ubuntu18.04 and Ubuntu20.04 - Cuda version - 10.2 and 11.6 - TensorRT version 8.0 and 8.4 ## About this repo I use...
## Env - GPU: Nano4GB. - OS:Ubuntu 18.04.5 LTS - Cuda version:10.2 - TensorRT version:7.1.3 ## About this repo - which model: yolov5s ## Your problem - what is your...
## Env - GPU, nano - OS, Ubuntu18.04 - Cuda version 10.2 - TensorRT version 8.0 ## About this repo - which branch/tag/commit are you using? efficientnet - which model?...
## Env - GPU, e.g. RTX3090 - OS, Centos 8 - Cuda version 11.2 - TensorRT version 8.4.1.5 ## About this repo - which branch/tag/commit are you using? - which...