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 cosine similarity and KL divergence results are NaN while other algorithms provide data, it indicates that either the actual data (to be compared) or the golden data (benchmark) of the operator is zero. If the KL divergence result is Inf, it indicates that at least one value in the benchmark data for the operator is zero.
- For common accuracy issues, output expert suggestions provided by Advisor to quickly locate faulty operators.
- 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.
- 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.
- For suspicious comparison results, check the accuracy issues according to Performing Accuracy Comparison Between .npy Files.
- For operators with large accuracy differences, you can use the Single-Operator Comparison function to further analyze the detailed accuracy differences of corresponding tensors.
- You can optimize faulty operators by modifying, replacing, or merging them based on specific scenarios.
Parent topic: Overview