mindspore.nn.Conv2dTranspose

View Source On Gitee
class mindspore.nn.Conv2dTranspose(in_channels, out_channels, kernel_size, stride=1, pad_mode='same', padding=0, output_padding=0, dilation=1, group=1, has_bias=False, weight_init=None, bias_init=None, dtype=mstype.float32)[source]

Calculates a 2D transposed convolution, which can be regarded as Conv2d for the gradient of the input, also called deconvolution (although it is not an actual deconvolution).

The input is typically of shape \((N, C_{in}, H_{in}, W_{in})\), where \(N\) is batch size, \(C_{in}\) is space dimension, \(H_{in}, W_{in}\) are the height and width of the feature layer respectively.

When Conv2d and Conv2dTranspose are initialized with the same parameters, and pad_mode is set to ‘pad’, \(dilation * (kernel\_size - 1) - padding\) amount of zero will be paded to the height and width directions of the input, they are inverses of each other in regard to the input and output shapes in this case. However, when stride > 1, Conv2d maps multiple input shapes to the same output shape. Deconvolutional network can refer to Deconvolutional Networks.

Parameters

  • in_channels (int) – The channel number of the input tensor of the Conv2dTranspose layer.

  • out_channels (int) – The channel number of the output tensor of the Conv2dTranspose layer.

  • kernel_size (Union[int, tuple[int]]) – Specifies the height and width of the 2D convolution kernel. The data type is an integer or a tuple of two integers. An integer represents the height and width of the convolution kernel. A tuple of two integers represents the height and width of the convolution kernel respectively.

  • stride (Union[int, tuple[int]]) – The movement stride of the 2D convolution kernel. The data type is an integer or a tuple of two integers. An integer represents the movement step size in both height and width directions. A tuple of two integers represents the movement step size in the height and width directions respectively. Default: 1 .

  • pad_mode (str, optional) –

    Specifies the padding mode with a padding value of 0. It can be set to: "same" , "valid" or "pad" . Default: "same" .

    • "same": Pad the input around its edges so that the shape of input and output are the same when stride is set to 1. The amount of padding to is calculated by the operator internally, If the amount is even, it is uniformly distributed around the input, if it is odd, the excess amount goes to the right/bottom side. If this mode is set, padding must be 0.

    • "valid": No padding is applied to the input, and the output returns the maximum possible height and width. Extra pixels that could not complete a full stride will be discarded. If this mode is set, padding must be 0.

    • "pad": Pad the input with a specified amount. In this mode, the amount of padding in the height and width directions is determined by the padding parameter. If this mode is set, padding must be greater than or equal to 0.

  • padding (Union[int, tuple[int]]) – The number of padding on the height and width directions of the input. The data type is an integer or a tuple of four integers. If padding is an integer, then the top, bottom, left, and right padding are all equal to padding. If padding is a tuple of 4 integers, then the top, bottom, left, and right padding is equal to padding[0], padding[1], padding[2], and padding[3] respectively. The value should be greater than or equal to 0. Default: 0 .

  • output_padding (Union[int, tuple[int]]) – The number of padding on the height and width directions of the output. The data type is an integer or a tuple of two integers. If output_padding is an integer, then the bottom and right padding are all equal to output_padding. If output_padding is a tuple of 2 integers, then the bottom and right padding is equal to output_padding[0], output_padding[1] respectively. If output_padding is not equal to 0, pad_mode must be pad. The value should be in range of [0, max(stride, dilation)) . Default: 0 .

  • dilation (Union[int, tuple[int]]) – Dilation size of 2D convolution kernel. The data type is an integer or a tuple of two integers. If \(k > 1\), the kernel is sampled every k elements. The value of k on the height and width directions is in range of [1, H] and [1, W] respectively. Default: 1 .

  • group (int) – Splits filter into groups, in_channels and out_channels must be divisible by group. Default: 1 .

  • has_bias (bool) – Whether the Conv2dTranspose layer has a bias parameter. Default: False .

  • weight_init (Union[Tensor, str, Initializer, numbers.Number]) – Initialization method of weight parameter. It can be a Tensor, a string, an Initializer or a numbers.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: None , weight will be initialized using HeUniform.

  • bias_init (Union[Tensor, str, Initializer, numbers.Number]) – Initialization method of bias parameter. Available initialization methods are the same as ‘weight_init’. Refer to the values of Initializer for more details. Default: None , bias will be initialized using Uniform.

  • dtype (mindspore.dtype) – Dtype of Parameters. Default: mstype.float32 .

Inputs:

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

Outputs:

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

pad_mode is 'same':

\[\begin{split}\begin{array}{ll} \\ H_{out} = \text H_{in}\times \text {stride[0]} \\ W_{out} = \text W_{in}\times \text {stride[1]} \\ \end{array}\end{split}\]

pad_mode is 'valid':

\[\begin{split}\begin{array}{ll} \\ H_{out} = \text H_{in}\times \text {stride[0]} + \max\{(\text{dilation[0]} - 1) \times (\text{kernel_size[0]} - 1) - \text {stride[0]}, 0 \} \\ W_{out} = \text W_{in}\times \text {stride[1]} + \max\{(\text{dilation[1]} - 1) \times (\text{kernel_size[1]} - 1) - \text {stride[1]}, 0 \} \\ \end{array}\end{split}\]

pad_mode is 'pad':

\[\begin{split}\begin{array}{ll} \\ H_{out} = \text H_{in}\times \text {stride[0]} - (padding[0] + padding[1]) + \text{kernel_size[0]} + (\text{dilation[0]} - 1) \times (\text{kernel_size[0]} - 1) - \text {stride[0]} + \text {output_padding[0]} \\ W_{out} = \text W_{in}\times \text {stride[1]} - (padding[2] + padding[3]) + \text{kernel_size[1]} + (\text{dilation[1]} - 1) \times (\text{kernel_size[1]} - 1) - \text {stride[1]} + \text {output_padding[1]} \\ \end{array}\end{split}\]
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 not a tuple.

  • 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’.

  • ValueError – If padding is a tuple whose length is not equal to 4.

  • ValueError – If pad_mode is not equal to ‘pad’ and padding is not equal to (0, 0, 0, 0).

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> net = nn.Conv2dTranspose(3, 64, 4, has_bias=False, weight_init='normal', pad_mode='pad')
>>> x = Tensor(np.ones([1, 3, 16, 50]), mindspore.float32)
>>> output = net(x).shape
>>> print(output)
(1, 64, 19, 53)