Preparing the Pipeline and Model

Preparing the Model

1. Download a model from the ModelZoo official website. The following uses YOLOv3 (version 1.6, TensorFlow) and ResNet-50 (version 1.7, TensorFlow) as examples to describe how to download models.
2. Decompress the packages and save the PB models to the ${MX_SDK_HOME}/sample/mxVision/models/YOLOV3 and ${MX_SDK_HOME}/sample/mxVision/models/resnet50 directories.
3. Convert the model by referring to Model Conversion to obtain an OM model. The permission on models and model-related files cannot be greater than 640.

Preparing the Pipeline

The sample pipeline is stored in ${MX_SDK_HOME}/sample/mxVision/pipeline/. To modify the element properties of a service flow in the pipeline configuration file or create a service flow, refer to the pipeline configuration file in the current path. (The Sample.pipeline file for image processing and Table 2 are used as examples.)