Deepstream skipping frames for inference

I am using deepstream with my own model. I trained my own model for action recognition. The model takes in 5 frames which are meant to be separated by 4 frames. The way I trained the model was by taking a 20-frame sample and feeding the model with the 1st, 5th, 10th, 15th, and 20th frames. So the model takes in 5 frames, but not 5 consecutive ones. I know that I can skip frames using the “interval” parameter. For instance, if I set the “interval” parameter to 4, will deepstream give my model frames [0, 1, 2, 3, 4] then frames [8, 9, 10, 11, 12]?( note that this is not my desired behavior since I don’t want consecutive frames fed into the model). If so, is there any way of feeding my model frames [0, 4, 9, 14, 19] then [24, 29, 34, 39, 44] and so on? Thanks!

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• 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)

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