torch_npu.contrib.DCNv2

torch_npu.contrib.DCNv2(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, deformable_groups=1, bias=True, pack=True)

应用基于NPU的调制可变形2D卷积操作。ModulationDeformConv的实现主要是基于mmcv的实现

进行设计和重构。

• 参数解释：
  • in_channels (int)：Number of channels in the input image.=
  • out_channels (int)：Number of channels produced by the convolution.
  • kernel_size(int, tuple)：Size of the convolving kernel.
  • stride(int, tuple)：Stride of the convolution. Default: 1.
  • padding (int or tuple)：Zero-padding added to both sides of the input.
  • Default：0.
  • dilation (int or tuple)：Spacing between kernel elements. Default：1.
  • groups (int)：Number of blocked connections from input.
  • channels to output channels. Default：1.
  • deform_groups (int)：Number of deformable group partitions.
  • bias (bool)：If True, adds a learnable bias to the output. Default：False.
  • pack (bool)：If True, conv_offset and mask will be included in this module. Default：True.
• 约束条件：

  ModedDeformConv仅实现fp32数据类型下的操作。注意，con_offset中的权重和偏置必须初始化为0。

• 示例：

     >>> m = ModulatedDeformConv(32, 32, 1)
     >>> input_tensor = torch.randn(2, 32, 5, 5)
     >>> output = m(input_tensor)
  
     >>> x = torch.randn(2, 32, 7, 7)
     >>> model = ModulatedDeformConv(32, 32, 3, 2, 1)
  
     >>> torch.npu.set_device(0)
     >>> x = x.npu()
     >>> model = model.npu()
  
     >>> o = model(x)
     >>> l = o.sum()
     >>> l.backward()
     >>> print(l)