{"version":"1.0","type":"rich","title":"zmq ml template","description":"A ZeroMQ REP socket on TCP port 5566 receives raw image frames as memory buffers, converts them to NumPy arrays, and feeds them through a preloaded Keras model for inference. The model processes each frame, clips the output to valid pixel ranges, concatenates an alpha channel, and sends the result back over the same socket. It logs inference and send times, calculates theoretical FPS, and handles errors by replying with an empty message.","provider_name":"VizHub AI Studio","provider_url":"https://next.vizhub.com","html":"<iframe src=\"https://next.vizhub.com/viz/gist-d187819d17a2ad15374da0ab2de60e93?mode=embed\" width=\"960\" height=\"500\" scrolling=\"no\" frameborder=\"1\"></iframe>","width":960,"height":500,"cache_age":3600}