Generating the Quantized Model - 3.5 English

Vitis AI User Guide (UG1414)

Document ID
Release Date
3.5 English

After the successful execution of the vai_q_tensorflow command, an output file is generated in ${output_dir}. Use quantize_eval_model.pb to evaluate the accuracy of the quantized model on CPU and GPUs and to simulate the results on hardware.

Table 1. vai_q_tensorflow Output Files
No. Name Description
1 deploy_model.pb Quantized model for the Vitis AI compiler (extended TensorFlow format) for targeting DPUCZDX8G implementations.
2 quantize_eval_model.pb Quantized model for evaluation (also, the Vitis AI compiler input for most DPU architectures, such as DPUCAHX8H and DPUCADF8H).