mindspore.nn.Conv1d

class mindspore.nn.Conv1d(in_channels, out_channels, kernel_size, stride=1, pad_mode='same', padding=0, dilation=1, group=1, has_bias=False, weight_init=None, bias_init=None)[source]

Calculates the 1D convolution on the input tensor. The input is typically of shape \((N, C_{in}, L_{in})\), where \(N\) is batch size, \(C_{in}\) is a number of channels and \(L_{in}\) is a length of sequence. For the tensor of each batch, its shape is \((C_{in}, L_{in})\), and the formula is defined as:

\[\text{out}(N_i, C_{\text{out}_j}) = \text{bias}(C_{\text{out}_j}) + \sum_{k = 0}^{C_{in} - 1} \text{ccor}({\text{weight}(C_{\text{out}_j}, k), \text{X}(N_i, k)})\]

where \(ccor\) is the cross-correlation, \(C_{in}\) is the channel number of the input, \(out_{j}\) corresponds to the \(j\)-th channel of the output and \(j\) is in the range of \([0, C_{out}-1]\). \(\text{weight}(C_{\text{out}_j}, k)\) is a convolution kernel slice with shape \(\text{kernel_size}\), where \(\text{kernel_size}\) is the width of the convolution kernel. \(\text{bias}\) is the bias parameter, and \(\text{X}\) is the input tensor. The shape of full convolution kernel is \((C_{out}, C_{in} / \text{group}, \text{kernel_size})\), where group is the number of groups to split the input x in the channel dimension.

For more details, please refers to the paper Gradient Based Learning Applied to Document Recognition.

Note

On Ascend platform, only group convolution in depthwise convolution scenarios is supported. That is, when group>1, condition in_channels = out_channels = group must be satisfied.

Parameters

  • in_channels (int) – The channel number of the input tensor of the Conv1d layer.

  • out_channels (int) – The channel number of the output tensor of the Conv1d layer.

  • kernel_size (int) – Specifies the width of the 1D convolution kernel.

  • stride (int) – The movement stride of the 1D convolution kernel. Default: 1 .

  • pad_mode (str) –

    Specifies padding mode. The optional values are "same" , "valid" , "pad" . Default: "same" .

    • "same": The width of the output is the same as the value of the input divided by stride. If this mode is set, the value of padding must be 0.

    • "valid": Returns a valid calculated output without padding. Excess pixels that do not satisfy the calculation will be discarded. If this mode is set, the value of padding must be 0.

    • "pad": Pads the input. Padding padding size of zero on both sides of the input. If this mode is set, the value of padding must be greater than or equal to 0.

  • padding (int) – The number of padding on both sides of input. The value should be greater than or equal to 0. Default: 0 .

  • dilation (int) – Dilation size of 1D convolution kernel. If \(k > 1\), the kernel is sampled every k elements. The value of k is in range of [1, L]. 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 Conv1d 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.

Inputs:

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

Outputs:

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

pad_mode is 'same':

\[L_{out} = \left \lceil{\frac{L_{in}}{\text{stride}}} \right \rceil\]

pad_mode is 'valid':

\[L_{out} = \left \lceil{\frac{L_{in} - \text{dilation} \times (\text{kernel_size} - 1) } {\text{stride}}} \right \rceil\]

pad_mode is 'pad':

\[L_{out} = \left \lfloor{\frac{L_{in} + 2 \times padding - (\text{kernel_size} - 1) \times \text{dilation} - 1 }{\text{stride}} + 1} \right \rfloor\]
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

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> net = nn.Conv1d(120, 240, 4, has_bias=False, weight_init='normal')
>>> x = Tensor(np.ones([1, 120, 640]), mindspore.float32)
>>> output = net(x).shape
>>> print(output)
(1, 240, 640)