mindspore.nn.Conv2dBnWithoutFoldQuant

class mindspore.nn.Conv2dBnWithoutFoldQuant(in_channels, out_channels, kernel_size, stride=1, pad_mode='same', padding=0, dilation=1, group=1, has_bias=False, eps=1e-05, momentum=0.997, weight_init='normal', bias_init='zeros', quant_config=quant_config_default, quant_dtype=QuantDtype.INT8)

2D convolution and batchnorm without fold with fake quantized construct.

This part is a more detailed overview of Conv2d operation. For more details about Quantization, please refer to the implementation of class of FakeQuantWithMinMaxObserver, mindspore.nn.FakeQuantWithMinMaxObserver.

\[ \begin{align}\begin{aligned}y =x\times quant(w)+ b\\y_{bn} =\frac{y-E[y] }{\sqrt{Var[y]+ \epsilon } } *\gamma + \beta\end{aligned}\end{align} \]

where \(quant\) is the continuous execution of quant and dequant, you can refer to the implementation of class of FakeQuantWithMinMaxObserver, mindspore.nn.FakeQuantWithMinMaxObserver.

Parameters

• in_channels (int) – The number of input channel \(C_{in}\).

• out_channels (int) – The number of output channel \(C_{out}\).

• kernel_size (Union[int, tuple[int]]) – Specifies the height and width of the 2D convolution window.

• stride (Union[int, tuple[int]]) – Specifies stride for all spatial dimensions with the same value. Default: 1.

• pad_mode (str) – Specifies padding mode. The optional values are “same”, “valid”, “pad”. Default: “same”.

• padding (Union[int, tuple[int]]) – Implicit paddings on both sides of the x. Default: 0.

• dilation (Union[int, tuple[int]]) – Specifies the dilation rate to use for dilated convolution. Default: 1.

• group (int) – Splits filter into groups, in_ channels and out_channels must be divisible by the number of groups. Default: 1.

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

• eps (float) – Parameters for Batch Normalization. Default: 1e-5.

• momentum (float) – Parameters for Batch Normalization op. Default: 0.997.

• weight_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the convolution kernel. Default: ‘normal’.

• bias_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the bias vector. Default: ‘zeros’.

• 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 \((N, C_{in}, H_{in}, W_{in})\).

Outputs:

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

Supported Platforms:

Ascend GPU

Raises

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

• TypeError – If kernel_size, stride, padding or dilation is neither an int nor a tuple.

• TypeError – If has_bias is not a bool.

• ValueError – If in_channels, out_channels, kernel_size, stride or dilation is less than 1.

• ValueError – If padding is less than 0.

• ValueError – If pad_mode is not one of ‘same’, ‘valid’, ‘pad’.

Examples

>>> import mindspore
>>> from mindspore.compression import quant
>>> from mindspore import Tensor
>>> qconfig = quant.create_quant_config()
>>> conv2d_no_bnfold = nn.Conv2dBnWithoutFoldQuant(1, 1, kernel_size=(2, 2), stride=(1, 1), pad_mode="valid",
...                                                weight_init='ones', quant_config=qconfig)
>>> x = Tensor(np.array([[[[1, 0, 3], [1, 4, 7], [2, 5, 2]]]]), mindspore.float32)
>>> result = conv2d_no_bnfold(x)
>>> print(result)
[[[[5.929658  13.835868]
   [11.859316  17.78116]]]]

extend_repr()

Display instance object as string.