Load a checkpoint and start the viewer.

usage: ns-viewer [-h] --load-config PATH [--viewer.relative-log-filename STR]
                 [--viewer.zmq-port {None}|INT]
                 [--viewer.websocket-port {None}|INT]
                 [--viewer.websocket-port-default INT]
                 [--viewer.ip-address STR]
                 [--viewer.max-num-display-images INT]
                 [--viewer.image-format {jpeg,png}]
                 [--viewer.jpeg-quality INT] [--viewer.png-compression INT]



Path to config YAML file. (required)

viewer arguments#

Viewer configuration


Filename to use for the log file. (default: viewer_log_filename.txt)


The zmq port to connect to for communication. If None, find an available port. (default: None)


whether or not to launch the bridge server (sets: launch_bridge_server=False)


The websocket port to connect to. If None, find an available port. (default: None)


The default websocket port to connect to if websocket_port is not specified (default: 7007)


the ip address where the bridge server is running (default:


Maximum number of training images to display in the viewer, to avoid lag. This does not change which images are actually used in training/evaluation. If -1, display all. (default: 512)


Whether to kill the training job when it has completed. Note this will stop rendering in the viewer. (sets: quit_on_train_completion=True)


Possible choices: jpeg, png

Image format viewer should use; jpeg is lossy compression, while png is lossless. (default: jpeg)


Quality tradeoff to use for jpeg compression. (default: 90)


Size/speed tradeoff to use for png compression. (default: 1)