--is_weight_clip

Description

Clips data when the upper bits of the floating-point weight data are converted to lower bits.

If the weight data type of the original model is high (for example, float32), the cast operator is inserted during model conversion to convert the data type from high (for example, float32) to low (for example, float16). In this scenario, data overflow may occur, by enabling the --is_weight_clip option, the upper-bit (for example, float32) data is cropped before the cast operator to prevent data overflow.

See Also

None

Argument

• 0: disabled.
• 1 (default): enabled.

Suggestions and Benefits

None

Example

--is_weight_clip=1

Applicability

Atlas 200/300/500 Inference Product

Atlas Training Series Product

Dependencies and Restrictions

None