Precision Comparison

QUANT_DUMPABLE

Sets whether to collect the dump data of the quantization operators. The corresponding options parameter is ge.quant_dumpable.

For details, see "Accuracy Improvement Suggestions for Model Inference" in the Application Development (C & C++). During precision locating, if there is a model after AMCT quantization, the input and output of the quantization operators may be optimized during graph build when the model is converted to an OM offline model, affecting the dump data export of the quantization operators. For example, for two quantized convolution calculations, the intermediate output is optimized to the quantized output of int8.

To solve this problem, the QUANT_DUMPABLE parameter is introduced. After this parameter is configured, the input and output of the quantization operator are not fused. The transdata operator is inserted to restore the original model format. In this way, the dump data of the quantization operator can be collected.

Parameter values:

• 0 (default): The inputs and outputs of the quantization operators may be optimized during graph build. In this case, the dump data of the quantization operators cannot be collected.
• 1: Dump data of the quantization operators cannot be collected.

Configuration example:

{ge::ir_option::QUANT_DUMPABLE, "1"}

Applicable products:

All processors