mindspore.nn.DenseQuant

class mindspore.nn.DenseQuant(in_channels, out_channels, weight_init='normal', bias_init='zeros', has_bias=True, activation=None, quant_config=quant_config_default, quant_dtype=QuantDtype.INT8)[source]

The fully connected layer with fake quantized operation.

This part is a more detailed overview of Dense operation. For more details about Quantization, please refer to the implementation of class of FakeQuantWithMinMaxObserver, mindspore.nn.FakeQuantWithMinMaxObserver.

Parameters
  • in_channels (int) – The dimension of the input space.

  • out_channels (int) – The dimension of the output space.

  • weight_init (Union[Tensor, str, Initializer, numbers.Number]) – The trainable weight_init parameter. The dtype is same as x. The values of str refer to the function initializer. Default: ‘normal’.

  • bias_init (Union[Tensor, str, Initializer, numbers.Number]) – The trainable bias_init parameter. The dtype is same as x. The values of str refer to the function initializer. Default: ‘zeros’.

  • has_bias (bool) – Specifies whether the layer uses a bias vector. Default: True.

  • activation (Union[str, Cell, Primitive]) – The regularization function applied to the output of the layer, eg. ‘relu’. Default: None.

  • quant_config (QuantConfig) – Configures the types of quant observer and quant settings of weight and activation. Note that, QuantConfig is a special namedtuple, which is designed for quantization and can be generated by mindspore.compression.quant.create_quant_config() method. Default: QuantConfig with both items set to default FakeQuantWithMinMaxObserver.

  • quant_dtype (QuantDtype) – Specifies the FakeQuant datatype. Default: QuantDtype.INT8.

Inputs:
  • x (Tensor) - Tensor of shape \((N, C_{in}, H_{in}, W_{in})\). The input dimension is preferably 2D or 4D.

Outputs:

Tensor of shape \((N, C_{out}, H_{out}, W_{out})\).

Raises
  • TypeError – If in_channels, out_channels is not an int.

  • TypeError – If has_bias is not a bool.

  • TypeError – If activation is not str, Cell and Primitive.

  • ValueError – If in_channels or out_channels is less than 1.

  • ValueError – If the dims of weight_init is not equal to 2 or the first element of weight_init is not equal to out_channels or the second element of weight_init is not equal to in_channels.

  • ValueError – If the dims of bias_init is not equal to 1 or the element of bias_init is not equal to out_channels.

Supported Platforms:

Ascend GPU

Examples

>>> import mindspore
>>> from mindspore.compression import quant
>>> from mindspore import Tensor
>>> qconfig = quant.create_quant_config()
>>> dense_quant = nn.DenseQuant(2, 1, weight_init='ones', quant_config=qconfig)
>>> x = Tensor(np.array([[1, 5], [3, 4]]), mindspore.float32)
>>> result = dense_quant(x)
>>> print(result)
[[5.929413]
 [6.9176483]]
construct(x)[source]

Use operators to construct the Dense layer.

extend_repr()[source]

A pretty print for Dense layer.