mindspore.nn.Conv1dTranspose

class mindspore.nn.Conv1dTranspose(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')[source]

1D transposed convolution layer.

Compute a 1D transposed convolution, which is also known as a deconvolution (although it is not an actual deconvolution). This module can be seen as the gradient of Conv1d with respect to its input.

x is typically of shape \((N, C, W)\), where \(N\) is batch size, \(C\) is channel number and \(W\) is the characteristic length.

The padding argument effectively adds \(dilation * (kernel\_size - 1) - padding\) amount of zero padding to both sizes of the input. So that when a Conv1d and a ConvTranspose1d are initialized with same parameters, they are inverses of each other in regard to the input and output shapes. However, when stride > 1, Conv1d maps multiple input shapes to the same output shape.

The width of output is defined as:

\[\begin{split}W_{out} = \begin{cases} (W_{in} - 1) \times \text{stride} - 2 \times \text{padding} + \text{dilation} \times (\text{ks_w} - 1) + 1, & \text{if pad_mode='pad'}\\ (W_{in} + \text{stride} - 1)/\text{stride}, & \text{if pad_mode='same'}\\ (W_{in} - 1) \times \text{stride} + \text{dilation} \times (\text{ks_w} - 1) + 1, & \text{if pad_mode='valid'} \end{cases}\end{split}\]

where \(\text{ks_w}\) is the width of the convolution kernel.

Parameters

  • in_channels (int) – The number of channels in the input space.

  • out_channels (int) – The number of channels in the output space.

  • kernel_size (int) – int, which specifies the width of the 1D convolution window.

  • stride (int) – The distance of kernel moving, an int number that represents the width of movement. Default: 1.

  • pad_mode (str) –

    Select the mode of the pad. The optional values are “pad”, “same”, “valid”. Default: “same”.

    • pad: Implicit paddings on both sides of the input x.

    • same: Adopted the way of completion.

    • valid: Adopted the way of discarding.

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

  • dilation (int) – The data type is 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 or equal to 1 and bounded by the width of the input x. Default: 1.

  • group (int) – Splits filter into groups, in_channels and out_channels must be divisible by the number of groups. This is not support for Davinci devices when group > 1. 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 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: ‘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’.

Inputs:

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

Outputs:

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

Raises

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

  • 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’.

Supported Platforms:

Ascend GPU CPU

Examples

>>> net = nn.Conv1dTranspose(3, 64, 4, has_bias=False, weight_init='normal', pad_mode='pad')
>>> x = Tensor(np.ones([1, 3, 50]), mindspore.float32)
>>> output = net(x).shape
>>> print(output)
(1, 64, 53)