AscendQuant

Description

Quantization operator.

Input

One input:

x: tensor of type float16 or float.

Output

One output:

y: tensor of type int8.

Attribute

offset of type float.

scale of type float.

sqrt_mode of type bool.

round_mode of type string.

ONNX Opset Support

Opset v8/v9/v10/v11/v12/v13/v14/v15/v16