--op_select_implmode

Description

Selects the operator implementation mode.

In high-precision mode, Newton's Method and Taylor's Formula is used to improve operator precision (fp16). In high-performance mode, the optimal performance is implemented without affecting the network precision (fp16).

See Also

None

Arguments

Arguments:

  • high_precision: high precision implementation mode
  • high_performance: high performance implementation mode

Default: high_performance

Suggestions and Benefits

None

Examples

--op_select_implmode=high_precision

Dependencies and Restrictions

Restrictions:

--op_select_implmode indicates the high-precision or high-performance mode of all operators. If an operator supports both high-precision and high-performance, the mode specified by --op_select_implmode is implemented during running. If an operator supports only high-precision or high-performance, the mode supported is implemented during running. For example:

If an operator supports only high-precision, and --op_select_implmode is set to high_performance, the --op_select_implmode parameter does not take effect and the high-precision mode is implemented.