Restrictions (Only for Inference Scenarios)

Restrictions

• The data to be compared should be obtained from the counterpart models. Otherwise, the comparison results of only the counterpart operators are displayed.
• 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 strided slice, L1 fusion, and L2 fusion), the comparison of the inputs or outputs of the operators is unavailable.
• When 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 unavailable.
• The path can contain only letters (a–z and A–Z), digits (0–9), and the following special characters: periods (.), forward slashes (/), backslashes (\), colons (:), underscores (_), and hyphens (-).

Description

• 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 Pre-Processing is switched on (for example, input of the data operator is set to YUV in AIPP), input format of the data operators may be different from that of the original model, leading to an unreliable comparison result.

• For an optimal experience, the following hardware configuration is recommended: 8-core CPU at 2.6 GHz with 16 GB memory.

• When the dump data generated by a quantized offline model running on the Ascend AI Processor is used as the data to be compared, intermediate operators that affect the accuracy exist between the quant and dequant operators, which cause great accuracy losses on the source data. Therefore, the intermediate operators are filtered out during accuracy comparison. In this case, the output result does not contain all operators on the entire network.