currentcommand lets you use the following submenu for the currently deployed site:
listcommand returns the ids of the sites that have been installed.
savecommand creates an archive that contains the given site, which can been installed on another server (e.g. offline)
loadcommand loads a site from an archive generated by a
upgradecommand install a new version of the site (using the latest docker-compose/kubernetes manifest from the api)
rollbackcommand reloads the nth previous version (upgrade followed by rollback 1 does nothing)
interventioncommand lets you interact with the customer API. There must then be a
customer-apiservice in your application to work. You can then use the create / delete / infer / status commands.
MODEL_VERSION_IDof the model version that you want to use within your application and the corresponding
Routing Key, you need to go on the Apps tab in the Deployment section and click on the app version that is deployed on your site.
MODEL_VERSION_IDis specified with the
ROUTING_KEYcorresponds to the rabbitMQ queue identifier.
AMPQ_URL. It corresponds to the rabbitMQ address. You will find this address in your server deployment files. It should look like
infer: Compute predictions only.
draw: Display the prediction result, whether tags or the bounding boxes.
blur: Blur the bounding boxes.
noop: Benchmark input and output processing capabilities.
inputoption. Below an example with each type of inputs.
-o frame %03d.jsonwill output
-o pred_%s.jpgwill output
outputoption. Below an example with each type of inputs.
-fand a long flag
--flag. Note that one use a simple
-while the other uses two
--. Also some options need an additional argument. Find below the option table. When indicated,
allmeans that all four commands