This section aims to demonstrate how to verify DPU inference result with VART tools. TensorFlow ResNet50, and PyTorch ResNet50 networks are used as examples. Following are the four steps for debugging the DPU with VART:
- Generate a quantized inference model and reference result.
- Generate a DPU xmodel.
- Generate a DPU inference result.
- Crosscheck the reference result and the DPU inference result.
Before you start to debug the DPU result, ensure that you have set up the environment according to the instructions in https://xilinx.github.io/Vitis-AI/docs/quickstart/vek280.html