Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) 3090
• DeepStream Version 7.1
• JetPack Version (valid for Jetson only)
• TensorRT Version deepstream 7.1 isntallation guide
• NVIDIA GPU Driver Version (valid for GPU only) 535
• Issue Type( questions, new requirements, bugs)
• 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)
این متن رو بفرست:
Hi,
I am using DeepStream Python bindings on a dGPU system with RTX 3090. My DeepStream version is 7.x and the NVIDIA driver version is 535.
I have a Python application where users can start and stop a DeepStream/GStreamer pipeline multiple times in the same process. The pipeline is recreated every time. On stop, I set the pipeline state to Gst.State.NULL and make loop , pipeline to none
The problem is that after every start/stop cycle, the process memory increases by about 300 MB. This happens even when I use the same model, same stream, and same pipeline structure(but i create new element and pipeline for every run). The memory does not return to the previous level after stopping the pipeline.
I attached an image of one of our pipeline graphs.
Run the application, start the pipeline, stop it, then start it again several times in the same Python process.
Example:
Run 1: memory increases and after stop called +300 MB memory remaind
Run 2: +300 MB remaind
Run 3: +300 MB remaind
Run 4: +300 MB remaind
...
is there any help