mindspore.ops.deformable_conv2d

mindspore.ops.deformable_conv2d(x, weight, offsets, kernel_size, strides, padding, bias=None, dilations=(1, 1, 1, 1), groups=1, deformable_groups=1, modulated=True)

Given 4D tensor inputs x, weight and offsets, compute a 2D deformable convolution. The deformable convolution operation can be expressed as follow:

Deformable Convolution v1:

$$y(p)=\sum _{k=1}^K{w}_k\cdot x(p+p_k+\mathrm{\Delta }{p}_k)$$

Deformable Convolution v2:

$$y(p)=\sum _{k=1}^K{w}_k\cdot x(p+p_k+\mathrm{\Delta }{p}_k)\cdot \mathrm{\Delta }{m}_k$$

Where $\mathrm{\Delta }{p}_k$ and $\mathrm{\Delta }{m}_k$ are the learnable offset and modulation scalar for the k-th location. For details, please refer to Deformable ConvNets v2: More Deformable, Better Results and Deformable Convolutional Networks.

Parameters

• x (Tensor) – A 4D tensor of input image. With the format "NCHW", the shape is $(N,C_{in},H_{in},W_{in})$. Dtype: float16 or float32.

• weight (Tensor) – A 4D tensor of learnable filters. Must have the same type as x. The shape is $(C_{out},C_{in}/groups,H_f,W_f)$.

• offsets (Tensor) – A 4D tensor of x-y coordinates offset and mask. With the format "NCHW", the shape is $(batch,3\ast deformable\mathrm{\_}groups\ast H_f\ast W_f,H_{out},W_{out})$. Note the C dimension is stored in the order of (offset_x, offset_y, mask). Must have the same type as x.

• kernel_size (tuple[int]) – A tuple of 2 integers. The size of kernel.

• strides (tuple[int]) – A tuple of 4 integers. The stride of the sliding window for each dimension of input. The dimension order is interpreted according to the data format of x. The N and C dimensions must be set to 1.

• padding (tuple[int]) – A tuple of 4 integers. The number of pixels to add to each (top, bottom, left, right) side of the input.

• bias (Tensor, optional) – An 1D tensor of additive biases to the filter outputs. The shape is $(C_{out})$. Default: None .

• dilations (tuple[int], optional) – A tuple of 4 integers. The dilation factor for each dimension of input. The dimension order is interpreted according to the data format of x. The N and C dimensions must be set to 1. Default: (1, 1, 1, 1) .

• groups (int, optional) – An integer of type int32. The number of blocked connections from input channels to output channels. In_channels and out_channels must both be divisible by groups. Default: 1 .

• deformable_groups (int, optional) – An integer of type int32. The number of deformable group partitions. In_channels must be divisible by deformable_groups. Default: 1 .

• modulated (bool, optional) – Specifies version of DeformableConv2D, True means v2, False means v1, currently only supports v2. Default: True .

Returns

Tensor, A 4D Tensor of output feature map. With the same type as x. With the format "NCHW", the shape is $(N,C_{out},H_{out},W_{out})$.

$$\begin{array}{r}\begin{array}{l}\\ H_{out}=\lfloor \frac{H_{in}+padding[0]+padding[1]-(H_f-1)\times \text{dilations[2]}-1}{\text{stride[0]}}+1\rfloor \\ W_{out}=\lfloor \frac{W_{in}+padding[2]+padding[3]-(W_f-1)\times \text{dilations[3]}-1}{\text{stride[1]}}+1\rfloor \end{array}\end{array}$$

Raises

• TypeError – If strides, padding, kernel_size or dilations is not a tuple with integer elements.

• TypeError – If modulated is not a bool.

• ValueError – If the tuple size of strides, padding, kernel_size or dilations is not expected.

• ValueError – The N or C dimensions of strides or dilations is not set to 1.

• ValueError – If modulated is not set to True.

Warning

This is an experimental API that is subject to change or deletion.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> from mindspore import dtype as mstype
>>> x = Tensor(np.ones((4, 3, 10, 10)), mstype.float32)
>>> kh, kw = 3, 3
>>> weight = Tensor(np.ones((5, 3, kh, kw)), mstype.float32)
>>> offsets = Tensor(np.ones((4, 3 * kh * kw, 8, 8)), mstype.float32)
>>> output = ops.deformable_conv2d(x, weight, offsets, (kh, kw), (1, 1, 1, 1), (0, 0, 0, 0))
>>> print(output.shape)
(4, 5, 8, 8)