Before executing vai_q_tensorflow, ensure that you have the frozen inference TensorFlow model in floating-point format and the calibration set ready, which should include the files listed in the following table.
|Floating-point frozen inference graph. Ensure that the graph is the inference graph rather than the training graph.
|A subset of the training dataset containing 100 to 1000 images.
|An input function to convert the calibration dataset to the input data of the frozen_graph during post-training quantization. Usually performs data pre-processing and augmentation.