mindspore.nn.FakeQuantWithMinMaxObserver

class mindspore.nn.FakeQuantWithMinMaxObserver(min_init=- 6, max_init=6, ema=False, ema_decay=0.999, per_channel=False, channel_axis=1, num_channels=1, quant_dtype=QuantDtype.INT8, symmetric=False, narrow_range=False, quant_delay=0)[source]

Quantization aware operation which provides the fake quantization observer function on data with min and max.

The running min/max \(x_{min}\) and \(x_{max}\) are computed as:

\[\begin{split}\begin{array}{ll} \\ x_{min} = \begin{cases} \min(\min(X), 0) & \text{ if } ema = \text{False} \\ \min((1 - c) \min(X) + \text{c } x_{min}, 0) & \text{ if } \text{otherwise} \end{cases}\\ x_{max} = \begin{cases} \max(\max(X), 0) & \text{ if } ema = \text{False} \\ \max((1 - c) \max(X) + \text{c } x_{max}, 0) & \text{ if } \text{otherwise} \end{cases} \end{array}\end{split}\]

where X is the input tensor, and \(c\) is the ema_decay.

The scale and zero point zp is computed as:

\[\begin{split}\begin{array}{ll} \\ scale = \begin{cases} \frac{x_{max} - x_{min}}{Q_{max} - Q_{min}} & \text{ if } symmetric = \text{False} \\ \frac{2\max(x_{max}, \left | x_{min} \right |) }{Q_{max} - Q_{min}} & \text{ if } \text{otherwise} \end{cases}\\ zp\_min = Q_{min} - \frac{x_{min}}{scale} \\ zp = \left \lfloor \min(Q_{max}, \max(Q_{min}, zp\_min)) + 0.5 \right \rfloor \end{array}\end{split}\]

where \(Q_{max}\) and \(Q_{min}\) is decided by quant_dtype, for example, if quant_dtype=INT8, then \(Q_{max} = 127\) and \(Q_{min} = -128\).

The fake quant output is computed as:

\[\begin{split}\begin{array}{ll} \\ u_{min} = (Q_{min} - zp) * scale \\ u_{max} = (Q_{max} - zp) * scale \\ u_X = \left \lfloor \frac{\min(u_{max}, \max(u_{min}, X)) - u_{min}}{scale} + 0.5 \right \rfloor \\ output = u_X * scale + u_{min} \end{array}\end{split}\]
Parameters

  • min_init (int, float) – The initialized min value. Default: -6.

  • max_init (int, float) – The initialized max value. Default: 6.

  • ema (bool) – The exponential Moving Average algorithm updates min and max. Default: False.

  • ema_decay (float) – Exponential Moving Average algorithm parameter. Default: 0.999.

  • per_channel (bool) – Quantization granularity based on layer or on channel. Default: False.

  • channel_axis (int) – Quantization by channel axis. Default: 1.

  • num_channels (int) – declarate the min and max channel size, Default: 1.

  • quant_dtype (QuantDtype) – The datatype of quantization, supporting 4 and 8bits. Default: QuantDtype.INT8.

  • symmetric (bool) – Whether the quantization algorithm is symmetric or not. Default: False.

  • narrow_range (bool) – Whether the quantization algorithm uses narrow range or not. Default: False.

  • quant_delay (int) – Quantization delay parameters according to the global step. Default: 0.

Inputs:

  • input (Tensor) - The input of FakeQuantWithMinMaxObserver.

Outputs:

Tensor, with the same type and shape as the input.

Raises

  • TypeError – If min_init or max_init is neither int nor float.

  • TypeError – If quant_delay is not an int.

  • TypeError – If min_init is not less than max_init.

  • TypeError – If quant_delay is not greater than or equal to 0.

Supported Platforms:

Ascend GPU

Examples

>>> fake_quant = nn.FakeQuantWithMinMaxObserver()
>>> input = Tensor(np.array([[1, 2, 1], [-2, 0, -1]]), mindspore.float32)
>>> output = fake_quant(input)
>>> print(output)
[[ 0.9882355  1.9764705  0.9882355]
 [-1.9764705  0.        -0.9882355]]