mindspore.nn.Conv2d

class mindspore.nn.Conv2d(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', data_format='NCHW')[source]

2D convolution layer.

Calculates the 2D convolution on the input tensor which is typically of shape \((N, C_{in}, H_{in}, W_{in})\), where \(N\) is batch size, \(C_{in}\) is a number of channels, \(H_{in}, W_{in}\) are the height and width of the feature layer respectively. For the tensor of each batch, its shape is \((C_{in}, H_{in}, W_{in})\), 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 jth 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 \((\text{kernel_size[0]}, \text{kernel_size[1]})\), where \(\text{kernel_size[0]}\) and \(\text{kernel_size[1]}\) are the height and width of the convolution kernel respectively. \(\text{bias}\) is the bias parameter and \(\text{X}\) is the input tensor. In this case, data_format of the input tensor is ‘NCHW’ and the shape of full convolution kernel is \((C_{out}, C_{in} / \text{group}, \text{kernel_size[0]}, \text{kernel_size[1]})\), where group is the number of groups to split the input x in the channel dimension. If data_format of the input tensor is ‘NHWC’, the shape of full convolution kernel will be \((C_{out}, \text{kernel_size[0]}, \text{kernel_size[1]}), C_{in} / \text{group}\).

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

Parameters

  • in_channels (int) – The channel number of the input tensor of the Conv2d layer.

  • out_channels (int) – The channel number of the output tensor of the Conv2d 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) –

    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 (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.

  • 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. If the group is equal to in_channels and out_channels, this 2D convolution layer also can be called 2D depthwise convolution layer. Default: 1.

  • has_bias (bool) – Whether the Conv2d 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: ‘normal’.

  • 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: ‘zeros’.

  • data_format (str) – The optional value for data format, is ‘NHWC’ or ‘NCHW’. Default: ‘NCHW’.

Inputs:

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

Outputs:

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

pad_mode is ‘same’:

\[\begin{split}\begin{array}{ll} \\ H_{out} ＝ \left \lceil{\frac{H_{in}}{\text{stride[0]}}} \right \rceil \\ W_{out} ＝ \left \lceil{\frac{W_{in}}{\text{stride[1]}}} \right \rceil \\ \end{array}\end{split}\]

pad_mode is ‘valid’:

\[\begin{split}\begin{array}{ll} \\ H_{out} ＝ \left \lceil{\frac{H_{in} - \text{dilation[0]} \times (\text{kernel_size[0]} - 1) } {\text{stride[0]}}} \right \rceil \\ W_{out} ＝ \left \lceil{\frac{W_{in} - \text{dilation[1]} \times (\text{kernel_size[1]} - 1) } {\text{stride[1]}}} \right \rceil \\ \end{array}\end{split}\]

pad_mode is ‘pad’:

\[\begin{split}\begin{array}{ll} \\ H_{out} ＝ \left \lfloor{\frac{H_{in} + padding[0] + padding[1] - (\text{kernel_size[0]} - 1) \times \text{dilation[0]} - 1 }{\text{stride[0]}} + 1} \right \rfloor \\ W_{out} ＝ \left \lfloor{\frac{W_{in} + padding[2] + padding[3] - (\text{kernel_size[1]} - 1) \times \text{dilation[1]} - 1 }{\text{stride[1]}} + 1} \right \rfloor \\ \end{array}\end{split}\]
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).

  • ValueError – If data_format is neither ‘NCHW’ not ‘NHWC’.

Supported Platforms:

Ascend GPU CPU

Examples

>>> net = nn.Conv2d(120, 240, 4, has_bias=False, weight_init='normal')
>>> x = Tensor(np.ones([1, 120, 1024, 640]), mindspore.float32)
>>> output = net(x).shape
>>> print(output)
(1, 240, 1024, 640)