--keep_dtype

Applicability

Product

Supported

Atlas A3 training products/Atlas A3 inference products

Atlas A2 training products/Atlas A2 inference products

Atlas 200I/500 A2 inference products

Atlas inference products

Atlas training products

Description

Keeps the computation precision of some operators unchanged during the compilation of the original network model.

In the inference scenario, --precision_mode can be used to set the global precision mode of a network model, but it may result in performance or accuracy problems on particular operators. Therefore, you can use --keep_dtype to keep the precision of these operators unchanged at build time.

See Also

Use this option in conjunction with --precision_mode. However, this option does not take effect when --precision_mode is set to must_keep_origin_dtype.

Arguments

Argument: directory (including the file name) of the operator configuration file, which lists operator names or operator types. Each operator must be in a separate line.

Restrictions:

Format: The directory (including the file name) can contain letters, digits, underscores (_), hyphens (-), periods (.), colons (:), and Chinese characters.

Suggestions and Benefits

None

Examples

  • To specify opnames, use the following template (named execeptionlist.cfg).
    Opname1
    Opname2
    ...
  • To specify optypes, use the following template (named execeptionlist.cfg).
    OpType::TypeName1
    OpType::TypeName2
    ...

The Relu operator in the TensorFlow ResNet50 network model is used as an example. The operator type defined by Ascend IR is Relu.

# Set the operator name.
fp32_vars/Relu
# Set the operator type.
OpType::Relu

Upload your execeptionlist.cfg file to any directory (for example, ${HOME}) on the server where AOE is located.

--keep_dtype=${HOME}/execeptionlist.cfg --precision_mode=force_fp16

During model compilation, the precision of the operators specified in the execeptionlist.cfg file will be preserved while those not specified in this file will be processed according to --precision_mode.

Dependencies and Restrictions

None