I created a tensorflow lite custom model and running it on a Raspberry pi. How can I test the model with pre-recorded video rather than the webcam?

I followed the process in this video to create my custom model…Train a custom object detection model using your data - YouTube

Hi @Tom_Platner,

One possibility is that extract the frames from video and pass those frames to the object detection model for inferencing. The older version of Raspberry Pi has less memory due to which loading a video of larger size might be a problem

Thank You