@@ -14,13 +14,19 @@ Deep neural nets often have some preprocessing steps on input data, and postproc
## How to define Node
### Simple series structure
PaddleServing has some predefined Computation Node in the framework. A very commonly used Computation Graph is the simple reader-inference-response mode that can cover most of the single model inference scenarios. A example graph and the corresponding DAG definition code is as follows.
For simple series logic, we simplify it and build it with `OpSeqMaker`. You can determine the successor by default according to the order of joining `OpSeqMaker` without specifying the successor of each node.
Since the code will be commonly used and users do not have to change the code, PaddleServing releases a easy-to-use launching command for service startup. An example is as follows:
An example containing multiple input nodes is given in the [MODEL_ENSEMBLE_IN_PADDLE_SERVING](MODEL_ENSEMBLE_IN_PADDLE_SERVING.md). A example graph and the corresponding DAG definition code is as follows.
For a graph with multiple input nodes, we need to use `OpGraphMaker` to build it, and you must give the predecessor of each node.
## More Examples
If a user has sparse features as inputs, and the model will do embedding lookup for each feature, we can do distributed embedding lookup operation which is not in the Paddle training computation graph. An example is as follows:
