Modifying the Model Definition - 1.4.1 English

Vitis AI User Guide (UG1414)

Document ID
Release Date
1.4.1 English
To make a PyTorch model quantizable, it is necessary to modify the model definition to make sure the modified model meets the following conditions. An example is available in Vitis AI GitHub.
  1. The model to be quantized should include forward method only. All other functions should be moved outside or move to a derived class. These functions usually work as pre-processing and post-processing. If they are not moved outside, the API removes them in the quantized module, which causes unexpected behavior when forwarding the quantized module.
  2. The float model should pass the jit trace test. Set the float module to evaluation status, then use the torch.jit.trace function to test the float model.