mindspore.nn.Conv3d

class mindspore.nn.Conv3d(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, data_format='NCDHW', dtype=mstype.float32)[source]

3D convolution layer.

Applies a 3D convolution over an input tensor which is typically of shape \((N, C_{in}, D_{in}, H_{in}, W_{in})\), where \(N\) is batch size, \(C\) is channel number, \(D, H, W\) are the depth, height and width of the feature map, respectively.

The output is calculated based on formula:

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

where \(bias\) is the output channel bias, \(ccor\) is the cross-correlation, \(weight\) is the convolution kernel value and \(X\) represents the input feature map.

Here are the indices' meanings:

  • \(i\) corresponds to the batch number, the range is \([0, N-1]\), where \(N\) is the batch size of the input.

  • \(j\) corresponds to the output channel, the range is \([0, C_{out}-1]\), where \(C_{out}\) is the number of output channels, which is also equal to the number of kernels.

  • \(k\) corresponds to the input channel, the range is \([0, C_{in}-1]\), where \(C_{in}\) is the number of input channels, which is also equal to the number of channels in the convolutional kernels.

Therefore, in the above formula, \({bias}(C_{out_j})\) represents the bias of the \(j\)-th output channel, \({weight}(C_{out_j}, k)\) represents the slice of the \(j\)-th convolutional kernel in the \(k\)-th channel, and \({X}(N_i, k)\) represents the slice of the \(k\)-th input channel in the \(i\)-th batch of the input feature map.

The shape of the convolutional kernel is given by \((\text{kernel_size[0]}, \text{kernel_size[1]}, \text{kernel_size[2]})\) where \(\text{kernel_size[0]}\) , \(\text{kernel_size[1]}\) and \(\text{kernel_size[2]}\) are the depth, height and width of the kernel, respectively. If we consider the input and output channels as well as the group parameter, the complete kernel shape will be \((C_{out}, C_{in} / \text{group}, \text{kernel_size[0]}, \text{kernel_size[1]}, \text{kernel_size[2]})\), where group is the number of groups dividing x's input channel when applying group convolution.

For more details about convolution layer, please refer to 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 Conv3d layer.

  • out_channels (int) – The channel number of the output tensor of the Conv3d layer.

  • kernel_size (Union[int, tuple[int]]) – Specifies the depth, height and width of the 3D convolution kernel. It can be a single int or a tuple of 3 integers. A single int means the value is for depth, height and the width. A tuple of 3 ints means the first value is for depth and the rest is for the height and width.

  • stride (Union[int, tuple[int]], optional) – The movement stride of the 3D convolution kernel. The data type is an integer or a tuple of three integers. An integer represents the movement step size in depth, height and width directions. A tuple of three integers represents the movement step size in the depth, 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 depth/height/width dimension 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 isuniformly distributed around the input, if it is odd, the excess amount goes to the front/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 depth, 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 depth, height and width dimension 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]), optional) – The number of padding on the depth, height and width directions of the input. The data type is an integer or a tuple of six integers. If padding is an integer, then the head, tail, top, bottom, left, and right padding are all equal to padding. If padding is a tuple of six integers, then the head, tail, top, bottom, left, and right padding is equal to padding[0], padding[1], padding[2], padding[3], padding[4] and padding[5] respectively. The value should be greater than or equal to 0. Default: 0 .

  • dilation (Union[int, tuple[int]], optional) – Specifies the dilation rate to use for dilated convolution. It can be a single int or a tuple of 3 integers. A single int means the dilation size is the same in the depth, height and width directions. A tuple of 3 ints represents the dilation size in the depth, height and width directions, respectively. Assuming \(dilation=(d0, d1, d2)\), the convolutional kernel samples the input with a spacing of \(d0-1\) elements in the depth direction, \(d1-1\) elements in the height direction, \(d2-1\) elements in the width direction respectively. The values in the depth, height and width dimensions are in the ranges [1, D], [1, H] and [1, W], respectively. Default: 1 .

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

  • has_bias (bool, optional) – Whether the Conv3d layer has a bias parameter. Default: False .

  • weight_init (Union[Tensor, str, Initializer, numbers.Number], optional) – 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], optional) –

    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' .

  • data_format (str, optional) – The optional value for data format. Currently only support 'NCDHW' .

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

Inputs:

  • x (Tensor) - Tensor of shape \((N, C_{in}, D_{in}, H_{in}, W_{in})\). Currently, input data type support float16 and float32 in CPU and GPU, and only float16 in Ascend.

Outputs:

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

pad_mode is 'same' :

\[\begin{split}\begin{array}{ll} \\ D_{out} = \left \lceil{\frac{D_{in}}{\text{stride[0]}}} \right \rceil \\ H_{out} = \left \lceil{\frac{H_{in}}{\text{stride[1]}}} \right \rceil \\ W_{out} = \left \lceil{\frac{W_{in}}{\text{stride[2]}}} \right \rceil \\ \end{array}\end{split}\]

pad_mode is 'valid' :

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

pad_mode is 'pad' :

\[\begin{split}\begin{array}{ll} \\ D_{out} = \left \lfloor{\frac{D_{in} + padding[0] + padding[1] - (\text{dilation[0]} - 1) \times \text{kernel_size[0]} - 1 }{\text{stride[0]}} + 1} \right \rfloor \\ H_{out} = \left \lfloor{\frac{H_{in} + padding[2] + padding[3] - (\text{dilation[1]} - 1) \times \text{kernel_size[1]} - 1 }{\text{stride[1]}} + 1} \right \rfloor \\ W_{out} = \left \lfloor{\frac{W_{in} + padding[4] + padding[5] - (\text{dilation[2]} - 1) \times \text{kernel_size[2]} - 1 }{\text{stride[2]}} + 1} \right \rfloor \\ \end{array}\end{split}\]
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 nor a tuple.

  • ValueError – If 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 6.

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

  • ValueError – If data_format is not 'NCDHW'.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore
>>> from mindspore import Tensor, nn
>>> import numpy as np
>>> x = Tensor(np.ones([16, 3, 10, 32, 32]), mindspore.float32)
>>> conv3d = nn.Conv3d(in_channels=3, out_channels=32, kernel_size=(4, 3, 3))
>>> output = conv3d(x)
>>> print(output.shape)
(16, 32, 10, 32, 32)