Skip to main content Module spatial Copy item path Source AttentionModuleOptions Options for attention. ConvOptions Convolution options. ConvTransposeOptions Transposed convolution options. DeformConvOptions Convolution options. GridSampleOptions Options for grid sampling operations. InterpolateOptions Interpolation options. PaddedConvOptions Convolution options with support for asymmetric padding. UnfoldOptions Unfold operation options. GridSamplePaddingMode Padding mode for grid sampling when coordinates are out of bounds. InterpolateMode Algorithm used for upsampling. calculate_conv_output_shape Calculate the expected output shape [batch_size, channels_out, spatial_dims, ..] for a convolution. calculate_conv_output_size Calculate the expected output size when doing a convolution operation. calculate_conv_output_sizes Calculate the expected output sizes when doing a convolution operation. calculate_conv_padding Calculate the expected padding size required when applying a convolution. calculate_conv_transpose_output_shape Calculate the expected output shape [batch_size, channels_out, spatial_dims, ..] for a transposed convolution. calculate_conv_transpose_output_size Calculate the expected output size when doing a transposed convolution operation. calculate_padding_out Compute the padding_out for a transpose conv that exactly recovers the
original size_in from size_out, accounting for any input elements the
forward conv dropped. Shared by conv{1,2,3}d_x_backward and the Ruda
dgrad fallback so the two paths can’t drift. calculate_pool_output_shape Calculate the expected output shape [batch_size, channels_out, spatial_dims, ..] for a pooling operation. calculate_pool_output_size Calculate the expected output size when doing a pooling operation. calculate_unfold_shape Calculate the output shape for an unfold operation. calculate_unfold_windows Calculate the number of unfolding windows that can be extracted from a dimension of given size.