模型开发接口
推理部署接口
API 相关说明
A Observer Module records input tensor’s running min and max values to calc scale.
mode (QuantMode) – set quantization mode.
QuantMode
eps (float) – a initial maximum value to avoid division by zero problem.
float
dtype (Union[str, QuantDtypeMeta]) – a string indicating which dtype to collect scale and zero_point of.
Union
str
QuantDtypeMeta
previous
Observer
next
SyncMinMaxObserver