mindspore.nn.Conv2dBnAct

class mindspore.nn.Conv2dBnAct(in_channels, out_channels, kernel_size, stride=1, pad_mode='same', padding=0, dilation=1, group=1, has_bias=False, weight_init='normal', bias_init='zeros', has_bn=False, momentum=0.997, eps=1e-05, activation=None, alpha=0.2, after_fake=True)[source]

A combination of convolution, Batchnorm, and activation layer.

This part is a more detailed overview of Conv2d operation.

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]) – The data type is int or a tuple of 2 integers. Specifies the height and width of the 2D convolution window. Single int means the value is for both height and width of the kernel. A tuple of 2 ints means the first value is for the height and the other is for the width of the kernel.

  • stride (int) – Specifies stride for all spatial dimensions with the same value. The value of stride must be greater than or equal to 1 and lower than any one of the height and width of the input. Default: 1.

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

  • padding (int) – Implicit paddings on both sides of the input. Default: 0.

  • dilation (int) – Specifies the dilation rate to use for dilated convolution. If set to be \(k > 1\), there will be \(k - 1\) pixels skipped for each sampling location. Its value must be greater than or equal to 1 and lower than any one of the height and width of the input. 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.

  • weight_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the convolution kernel. It can be a Tensor, a string, an Initializer or a number. When a string is specified, values from ‘TruncatedNormal’, ‘Normal’, ‘Uniform’, ‘HeUniform’ and ‘XavierUniform’ distributions as well as constant ‘One’ and ‘Zero’ distributions are possible. Alias ‘xavier_uniform’, ‘he_uniform’, ‘ones’ and ‘zeros’ are acceptable. Uppercase and lowercase are both acceptable. Refer to the values of Initializer for more details. Default: ‘normal’.

  • bias_init (Union[Tensor, str, Initializer, numbers.Number]) – Initializer for the bias vector. Possible Initializer and string are the same as ‘weight_init’. Refer to the values of Initializer for more details. Default: ‘zeros’.

  • has_bn (bool) – Specifies to used batchnorm or not. Default: False.

  • momentum (float) – Momentum for moving average for batchnorm, must be [0, 1]. Default:0.9

  • eps (float) – Term added to the denominator to improve numerical stability for batchnorm, should be greater than 0. Default: 1e-5.

  • activation (Union[str, Cell, Primitive]) – Specifies activation type. The optional values are as following: ‘softmax’, ‘logsoftmax’, ‘relu’, ‘relu6’, ‘tanh’, ‘gelu’, ‘sigmoid’, ‘prelu’, ‘leakyrelu’, ‘hswish’, ‘hsigmoid’. Default: None.

  • alpha (float) – Slope of the activation function at x < 0 for LeakyReLU. Default: 0.2.

  • after_fake (bool) – Determine whether there must be a fake quantization operation after Cond2dBnAct.

Inputs:

  • input (Tensor) - Tensor of shape \((N, C_{in}, H_{in}, W_{in})\).

Outputs:

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

Raises

  • TypeError – If in_channels, out_channels, stride, padding or dilation is not an int.

  • TypeError – If has_bias is not a bool.

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

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

Supported Platforms:

Ascend GPU CPU

Examples

>>> net = nn.Conv2dBnAct(120, 240, 4, has_bn=True, activation='relu')
>>> input = Tensor(np.ones([1, 120, 1024, 640]), mindspore.float32)
>>> result = net(input)
>>> output = result.shape
>>> print(output)
(1, 240, 1024, 640)