文档

Comparison Result Analysis Guide

  • The asterisk (*) indicates that a new unique operator on the NPU does not have a corresponding standard operator. In this case, comparison is unavailable and NaN is displayed.
  • If the results of cosine similarity and Kullback-Leibler divergence are NaN, and the results of other algorithms exist, at least one piece of data on the left or the right is 0. If the result of Kullback-Leibler divergence is inf, one piece of data on the right is 0.
  1. For common accuracy issues, output expert suggestions provided by Advisor to quickly locate faulty operators.
  2. For complex scenarios that cannot be covered by expert suggestions, you can view different algorithm indicators in the network-wide comparison results and locate operators with accuracy issues based on Computation Accuracy Evaluation Indicators.
  3. In scenarios with multiple comparisons or fuzzy issue demarcation, you can configure the -r or -s option to achieve accuracy comparison within any selected range of operators, especially for large-scale networks, enabling rapid location of accuracy issues. For details about the -r or -s option, see Command Syntax.
  4. For suspicious comparison results, check the accuracy issues according to Performing Accuracy Comparison Between .npy Files.
  5. For operators with large accuracy differences, you can use the Single-Operator Comparison function to further analyze the detailed accuracy differences of corresponding tensors.
  6. You can optimize faulty operators by modifying, replacing, or merging them based on specific scenarios.