mindspore.ops.DepthwiseConv2dNative

class mindspore.ops.DepthwiseConv2dNative(*args, **kwargs)[source]

Returns the depth-wise convolution value for the input.

Applies depthwise conv2d for the input, which will generate more channels with channel_multiplier. Given an input tensor of shape \((N, C_{in}, H_{in}, W_{in})\) where \(N\) is the batch size, \(C\) is the channels, \(H\) is height, \(W\) is width and a filter tensor with kernel size \((ks_{h}, ks_{w})\), where \(ks_{h}\) indicates the kernel_size of height, \(ks_{w}\) indicates the kernel_size of width, containing \(C_{in} * \text{channel_multiplier}\) convolutional filters of depth 1; it applies different filters to each input channel (channel_multiplier channels for each input channel has the default value 1), then concatenates the results together. The output has \(C_{in} * \text{channel_multiplier}\) channels.

Parameters

  • channel_multiplier (int) – The multiplier for the original output convolution. Its value must be greater than 0.

  • kernel_size (Union[int, tuple[int]]) – The size of the convolution kernel.

  • mode (int) – Modes for different convolutions. 0 Math convolution, 1 cross-correlation convolution , 2 deconvolution, 3 depthwise convolution. Default: 3.

  • pad_mode (str) – Modes to fill padding. It could be “valid”, “same”, or “pad”. Default: “valid”.

  • pad (Union[int, tuple[int]]) – The pad value to be filled. If pad is an integer, the paddings of top, bottom, left and right are the same, equal to pad. If pad is a tuple of four integers, the padding of top, bottom, left and right equal to pad[0], pad[1], pad[2], and pad[3] correspondingly. Default: 0.

  • stride (Union[int, tuple[int]]) – The stride to be applied to the convolution filter. Default: 1.

  • dilation (Union[int, tuple[int]]) – Specifies the dilation rate to be used for the dilated convolution. Default: 1.

  • group (int) – Splits input into groups. Default: 1.

Inputs:

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

  • weight (Tensor) - Set the size of kernel as \((ks_{h}, ks_{w})\), then the shape is \((K, C_{in}, ks_{h}, ks_{w})\), K must be 1.

Outputs:

Tensor of shape \((N, C_{in} * \text{channel_multiplier}, H_{out}, W_{out})\).

Raises

  • TypeError – If kernel_size, stride, pad or dilation is neither an int nor a tuple.

  • TypeError – If channel_multiplier or group is not an int.

  • ValueError – If stride or dilation is less than 1.

  • ValueError – If pad_mode is not one of the following:’same’, ‘valid’ or ‘pad’.

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

Supported Platforms:

Ascend

Examples

>>> input_tensor = Tensor(np.ones([10, 32, 32, 32]), mindspore.float32)
>>> weight = Tensor(np.ones([1, 32, 3, 3]), mindspore.float32)
>>> depthwise_conv2d = ops.DepthwiseConv2dNative(channel_multiplier=3, kernel_size=(3, 3))
>>> output = depthwise_conv2d(input_tensor, weight)
>>> print(output.shape)
(10, 96, 30, 30)