Preparing the Float Model and Related Input Files - 3.5 English

Vitis AI User Guide (UG1414)

Document ID
UG1414
Release Date
2023-09-28
Version
3.5 English

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.

Table 1. Input Files for vai_q_tensorflow
No. Name Description
1 frozen_graph.pb Floating-point frozen inference graph. Ensure that the graph is the inference graph rather than the training graph.
2 calibration dataset A subset of the training dataset containing 100 to 1000 images.
3 input_fn 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.