Image Classification Prediction

To use the prediction service, users must fill in the 'prediction' section of the user_config.yaml file like the prediction_config.yaml or as shown in the example below:

general:

model: 
   model_path: <path-to-a-Keras-or-TFlite-model-file>           # Path to the model to use to make predictions

operation_mode: prediction

dataset:
   dataset_name: tf_flowers
   class_names: [daisy, dandelion, roses, sunflowers, tulips]   # Names of the classes
   prediction_path: ./datasets/flower_predict   # Path to the directory containing the images to predict

preprocessing:
   rescaling:
      scale: 1/127.5
      offset: -1
   resizing:
      interpolation: nearest
      aspect_ratio: False
   color_mode: rgb

mlflow:
   uri: ./tf/src/experiments_outputs/mlruns

hydra:
   run:
      dir: ./tf/src/experiments_outputs/${now:%Y_%m_%d_%H_%M_%S}

In the model section, users must provide the path to their model file using the model_path attribute. This can be either a Keras model file with a '.keras' filename extension (float model), a '.onnx' model or a TensorFlow Lite model file with a '.tflite' filename extension (quantized model).

The dataset section requires users to provide the names of the classes using the class_names or the classes_file_path the attribute pointing to a text file containing the class names, as there is no dataset available to infer them. prediction_path is the path to the directory containing the images to predict must also be provided here.

If users are using a quantized TFLITE or ONNX model, they can decide to do the inferences with the classic Python interpreters (host -> by default), with the C code generated by stedgeai on the PC (stedgeai_host), or with the C code generated by stedgeai on the N6 board directly (stedgeai_n6) using the target attribute. Hereafter, an example is provided for the N6:

prediction:
   profile: profile_O3
   input_type: uint8     # int8 / uint8 / float32
   output_type: int8     # int8 / uint8 / float32
   input_chpos: chlast   # chlast / chfirst
   output_chpos: chlast  # chlast / chfirst
   target: stedgeai_n6   # host, stedgeai_host, stedgeai_n6

Finally, once all of these sections have been filled in, users can run the prediction service to generate predictions for their set of images.

Hydra and MLflow Settings

The mlflow and hydra sections must always be present in the YAML configuration file. The hydra section can be used to specify the name of the directory where experiment directories are saved and/or the pattern used to name experiment directories. With the YAML code below, every time you run the Model Zoo, an experiment directory is created that contains all the directories and files created during the run. The names of experiment directories are all unique as they are based on the date and time of the run.

hydra:
   run:
      dir: ./tf/src/experiments_outputs/${now:%Y_%m_%d_%H_%M_%S}

The mlflow section is used to specify the location and name of the directory where MLflow files are saved, as shown below:

mlflow:
   uri: ./tf/src/experiments_outputs/mlruns

If you chose to modify the user_config.yaml, you can evaluate the model by running the following command from the UC folder:

python stm32ai_main.py 

If you chose to update the prediction_config.yaml and use it, then run the following command from the UC folder:

python stm32ai_main.py --config-path ./config_file_examples/ --config-name prediction_config.yaml