Graphs Repository

Model server can deploy a pipelines of models and nodes for any complex and custom transformations. From the client perspective it behaves almost like a single model, but it is more flexible and configurable.

The model repository employing graphs is similar in the structure to classic models. It needs to include the collection of models used in the pipeline. It also requires a MediaPipe graph definition file in .pbtxt format.

graph_models
├── graph.pbtxt
├── model.py
├── model1
│   └── 1
│       ├── model.bin
│       └── model.xml
├── model2
│   └── 1
│       ├── model.bin
│       └── model.xml
└── config.json

In case the graph includes python nodes, there should be included also a python file with the node implementation.

Note: Idle servable management (preview) can unload inactive graph groups and reload them on inference request. Set group_name in graph configuration to load and unload related servables together.

For more information on how to use MediaPipe graphs, refer to the article. Check also the documentation about python nodes