Command line reference
Installing mozo installs the mozo command. mozo --help lists the commands and
mozo <command> --help the options of one.
mozo start
mozo start [--host HOST] [--port PORT] [--workers N] [--reload]Start the HTTP server.
| Option | Default | Description |
|---|---|---|
--host |
0.0.0.0 |
Address to listen on. |
--port |
8000 |
Port to listen on. |
--workers |
1 |
Worker processes. Each loads its own copy of every model it serves, so memory grows with each one. |
--reload |
off | Restart when the code changes, for development. Forces one worker. |
The server reads MOZO_ENABLE, MOZO_CACHE, MOZO_OFFLINE, MOZO_BASE_URL and
MOZO_PREPARED_MB from the environment; Configuration has
them. HTTP server is the guide.
mozo run
mozo run WORKFLOW [--file PATH] [--set NAME=VALUE ...] [--test]Run a workflow from a JSON file, with no browser and no server. It runs over the whole source: every image in a folder, every frame of a video. Progress is printed as it goes; nodes that write files have written them when it ends.
| Option | Description |
|---|---|
--file |
Run on this image, video or folder instead of the one saved in the workflow. |
--set NAME=VALUE |
Override a parameter, by name or as node.name for one node's. Repeatable. |
--test |
Run one item and print what every node produced, instead of the whole source. |
mozo run blur_faces.json --file example.jpg --set threshold=0.5Blur faces -- Find every face and blur it.
1 item in 2.8s (0/s)--test describes each node's output in a line: an image's size, how many detections and of what,
a depth map's range. Use it to check a graph does its job before you point it at ten thousand
files:
Blur faces -- Find every face and blur it.
read: a 1920x1281 image
find: 5 x ['face']
blur: a 1920x1281 image
save: nothing (an end)Run a workflow covers the same from Python.
mozo version
mozo versionMozo version 1.10.0