Disable frame batching from same stream - batch only from different streams in Deepstream

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 6.2 Triton
• TensorRT Version 8.5.2
• NVIDIA GPU Driver Version (valid for GPU only) Driver Version: 525.85.05 CUDA Version: 12.0
• Issue Type( questions, new requirements, bugs) Question
• 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)

  1. Use old nvstreammux, set batch size > 1
  2. Use multisrcbin, set max batch size > 1

I am using a pipeline with LSTM model with dynamic batching. Since I am using a statefull model, I need to disable batching of frames from the same stream, but allow batching of frames from several streams.

I currently cannot find how to perform this.

Any insights?


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

please refer to nvstreammux’s doc doc, especially here "The muxer uses a round-robin algorithm to collect frames from the sources. It tries to collect an average of (batch-size/num-source) frames per batch from each source ", you might set nvstreammux 's batch-size to source 's num.

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