DeformConv2d

class torchvision.ops.DeformConv2d(in_channels: int, out_channels: int, kernel_size: int, stride: int = 1, padding: int = 0, dilation: int = 1, groups: int = 1, bias: bool = True)

参见 deform_conv2d()。

forward(input: Tensor, offset: Tensor, mask: Optional[Tensor] = None) → Tensor

参数：

• input (Tensor[batch_size, in_channels, in_height, in_width]) – 输入张量

• offset (Tensor[batch_size, 2 * offset_groups * kernel_height * kernel_width, out_height, out_width]) – 应用于卷积核中每个位置的偏移量。

• mask (Tensor[batch_size, offset_groups * kernel_height * kernel_width, out_height, out_width]) – 应用于卷积核中每个位置的掩码。