ns-viewer#

Load a checkpoint and start the viewer.

usage: ns-viewer [-h] [OPTIONS]

options#

-h, --help

show this help message and exit

--load-config

Path to config YAML file. (required)

--vis

Possible choices: viewer, viewer_legacy

Type of viewer (default: viewer)

viewer options#

Viewer configuration

--viewer.relative-log-filename

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

--viewer.websocket-port

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

--viewer.websocket-port-default

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

--viewer.websocket-host

The host address to bind the websocket server to. (default: 0.0.0.0)

--viewer.max-num-display-images

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)

--viewer.quit-on-train-completion

Possible choices: True, False

Whether to kill the training job when it has completed. Note this will stop rendering in the viewer. (default: False)

--viewer.image-format

Possible choices: jpeg, png

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

--viewer.jpeg-quality

Quality tradeoff to use for jpeg compression. (default: 75)

--viewer.make-share-url

Possible choices: True, False

Viewer beta feature: print a shareable URL. This flag is ignored in the legacy version of the viewer. (default: False)

--viewer.camera-frustum-scale

Scale for the camera frustums in the viewer. (default: 0.1)

--viewer.default-composite-depth

Possible choices: True, False

The default value for compositing depth. Turn off if you want to see the camera frustums without occlusions. (default: True)