By default, Frigate will use a single CPU detector. If you have a Coral, you will need to configure your detector devices in the config file. When using multiple detectors, they run in dedicated processes, but pull from a common queue of requested detections across all cameras.
cpu as detector types. The device value should be specified according to the Documentation for the TensorFlow Lite Python API.
Note: There is no support for Nvidia GPUs to perform object detection with tensorflow. It can be used for ffmpeg decoding, but not object detection.
warning: may have compatibility issues after
When using CPU detectors, you can add a CPU detector per camera. Adding more detectors than the number of cameras should not improve performance.