i tried a solution long before , basically i set up a kafka server and built a whole ecosystem of training,detection and reporting around it with different programs on a single machine but simple could be scaled by using VMs and multiple machines . this don't have to wait for frames and also you can choose which frame should be sent to which cycle( like training or detection).
--- [Visit Topic](https://discuss.mxnet.apache.org/t/object-detection-reading-from-rtsp-stream-with-no-buffer/6591/2) or reply to this email to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.mxnet.apache.org/email/unsubscribe/e860ec86ced8d523fbdf840b19b26251d4d6950ace38cad4fdff6a83efd8164c).
