Deserialize yoloLayer plugin: (Unnamed Layer* 256) [PluginV2IOExt]

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

jetpack 4.6.1
xavier nx
cuda arch 7.2.2
cuda 10.2
opencv 4.1.1
TensorRt 8.2.1.8
cudnn 8.2.1.32
deepstream-app version 6.0.1
DeepstreamSDK 6.0.1
deepstram-python 1.1.1
weights : yolov5-v7
我训练的自己的模型，通过：GitHub - marcoslucianops/DeepStream-Yolo: NVIDIA DeepStream SDK 6.1.1 / 6.1 / 6.0.1 / 6.0 configuration for YOLO models 该项目当中提供的模型转换，已经转换成engine模型，之后在也编译了libnvdsinfer_custom_impl_Yolo.so。之后首先使用
deepstram-app 直接运行转后的engine模型，可以正常进行识别视频，没有问题。但是，当我将该模型放在deepstram-python 当中的时候，进行视频识别的时候遇到了：
Deserialize yoloLayer plugin: (Unnamed Layer* 256) [PluginV2IOExt]
这个问题。
请问这个该如何解决。

1 Like
3

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks
Because global customers may refer to this problem, please convert the topic into English. Thanks
How did you run with deepstream-app and how did you put the model into deepstream-python?

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.