Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
GPU • DeepStream Version
DeepStream 6.1 • JetPack Version (valid for Jetson only) • TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
CUDA 11.6 • Issue Type( questions, new requirements, bugs)
new requirements • How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
使用deepstream部署视频检测模型,配置多个视频源,想指定每个视频源使用的gpu-id,让多个GPU能够同时工作,配置文件如下,如何让多gpu同时工作,或者能否这样配置?
As you know, there are many gstreamer elements in pipeline, for example: decoding, videoconvert, inference. these elements can set own gpu-id, you can refer to DeepStream Reference Application - deepstream-app — DeepStream 6.1.1 Release documentation
in this picture, gpu-id is used in source part, like video decoding, will not be set to inference part.
1 you can start multiple processes, only need to modify the configuration file, set different gpu-id.
2 if want to start in one process, you need to modify code, for example: source0 uses gpu0 to decoding and inference, source1 uses gpu1 to decoding and inference.