vis4d.op.layer.deform_conv

Wrapper for deformable convolution.

Classes

DeformConv(in_channels, out_channels, ...[, ...])

Wrapper around Deformable Convolution operator with norm/activation.

class DeformConv(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True, norm=None, activation=None)

Wrapper around Deformable Convolution operator with norm/activation.

If norm is specified, it is initialized with 1.0 and bias with 0.0.

Creates an instance of the class.

Parameters:

• in_channels (int) – Input channels.

• out_channels (int) – Output channels.

• kernel_size (int) – Size of convolutional kernel.

• stride (int, optional) – Stride of convolutional layer. Defaults to 1.

• padding (int, optional) – Padding of convolutional layer. Defaults to 0.

• dilation (int, optional) – Dilation of convolutional layer. Defaults to 1.

• groups (int, optional) – Number of deformable groups. Defaults to 1.

• bias (bool, optional) – Whether to use bias in convolutional layer. Defaults to True.

• norm (nn.Module, optional) – Normalization layer. Defaults to None.

• activation (nn.Module, optional) – Activation layer. Defaults to None.

forward(input_x)

Forward.

Return type:

Tensor

init_weights()

Initialize weights of offset conv layer.

Return type:

None