Comparison Result Description

This section describes the comparison results in which some items cannot be compared or exceptions occur (for example, NaN in the results).

• For Caffe or TensorFlow models, if the data comes from different models but the models contain comparable operators with the same names, the comparison can also be performed, but the comparison results of only the counterpart operators are displayed. This scenario is not analyzed.
• During graph build, if some operators of the graph are fused, the outputs of these operators can no longer be found in the built model. As a result, the comparison of these operators is unavailable.
• During graph build, if the structure of a graph is modified (such as stride, L1 fusion, and L2 fusion), the comparison of the inputs or outputs of the operators is unavailable.
• If the counterpart operators require different shapes (for example, the offline model operator requires a reduced shape), or format conversion is not supported, the comparison of these operators is unavailable.
• In a quantized model, the comparison of quantized operators is available only after they are dequantized. For example, in a quantized model, the comparison of the output of the AscendQuant operator is not available.
• For the Fast R-CNN network, the comparison result is subject to the accuracy of the FSRDetectionOutput operators. It is justifiable that the ProposalD operator and its downstream operators offer low accuracy.
• If data is preprocessed (for example, the input of the data operators is set to YUV in AIPP), the input format of the data operators may be different from that of the original model, leading to an unreliable comparison result.
• If counterpart operators have multiple inputs in different orders, the input comparison result of these operators is inaccurate.
• If the corresponding fusion pattern is enabled, a quantized operator will be fused with its upstream operator. As a result, the comparison result of the operator output is unreliable.