# tensorplay.functional.fake_quantize_per_channel_affine

Source: https://www.tensorplay.cn/docs/generated/tensorplay.functional.fake_quantize_per_channel_affine.html

```python
tensorplay.functional.fake_quantize_per_channel_affine(input, scale, zero_point, axis, quant_min, quant_max) → Tensor
```

Returns a new tensor with the data in input fake quantized per channel using scale,
zero_point, quant_min and quant_max, across the channel specified by axis.

$$\text{output} = (
    min(
        \text{quant\_max},
        max(
            \text{quant\_min},
            \text{std::nearby\_int}(\text{input} / \text{scale}) + \text{zero\_point}
        )
    ) - \text{zero\_point}
) \times \text{scale}$$

Parameters:

- input ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – the input value(s), in tensorplay.float32

- scale ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – quantization scale, per channel in tensorplay.float32

- zero_point ([Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)) – quantization zero_point, per channel in tensorplay.int32 or tensorplay.half or tensorplay.float32

- axis (int32) – channel axis

- quant_min (int64) – lower bound of the quantized domain

- quant_max (int64) – upper bound of the quantized domain

Returns:

A newly fake_quantized per channel tensorplay.float32 tensor

Return type:

[Tensor](/docs/generated/tensorplay.Tensor.html#tensorplay.Tensor)

Example:

```
>>> x = tensorplay.randn(2, 2, 2)
>>> x
tensor([[[-0.2525, -0.0466],
         [ 0.3491, -0.2168]],

        [[-0.5906,  1.6258],
         [ 0.6444, -0.0542]]])
>>> scales = (tensorplay.randn(2) + 1) * 0.05
>>> scales
tensor([0.0475, 0.0486])
>>> zero_points = tensorplay.zeros(2).to(tensorplay.int32)
>>> zero_points
tensor([0, 0])
>>> tensorplay.fake_quantize_per_channel_affine(x, scales, zero_points, 1, 0, 255)
tensor([[[0.0000, 0.0000],
         [0.3405, 0.0000]],

        [[0.0000, 1.6134],
        [0.6323, 0.0000]]])
```