diff options
Diffstat (limited to 'chapters/type_conversion.adoc')
-rw-r--r-- | chapters/type_conversion.adoc | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/chapters/type_conversion.adoc b/chapters/type_conversion.adoc index 1427374..7d0682a 100644 --- a/chapters/type_conversion.adoc +++ b/chapters/type_conversion.adoc @@ -84,8 +84,8 @@ Rescale quantized values into a new domain. This function scales by factor: mult |Output|out_t*|output|shape|Output tensor with the same shape as input |Attribute|in_t|input_zp|-|Input tensor zero point. Must be zero for non-int8 types. |Attribute|out_t|output_zp|-|Output tensor zero point. Must be zero for non-int8 types. -|Input (MT profile) Attribute (BI/MI profiles)|mul_t|multiplier|[NC]|Scaling multiplier array -|Input (MT profile) Attribute (BI/MI profiles)|uint6_t|shift|[NC]|Scaling shift array +|Input (MT profile) Attribute (BI/MI profiles)|mul_t*|multiplier|[NC]|Scaling multiplier array +|Input (MT profile) Attribute (BI/MI profiles)|uint6_t*|shift|[NC]|Scaling shift array |Attribute|bool_t|scale32|-|if (scale32) mul_t=int32_t else mul_t=int16_t |Attribute|bool_t|double_round|-|Select double round mode |Attribute|bool_t|per_channel|-|if (per_channel) NC=shape[dims-1] else NC=1 |