For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo function

conv_transpose_shape

def conv_transpose_shape[dtype: DType, strides_type: DType, dilations_type: DType, pads_type: DType, output_pads_type: DType](input: TileTensor[dtype, Storage=input.Storage, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size], kernel: TileTensor[dtype, Storage=kernel.Storage, address_space=kernel.address_space, linear_idx_type=kernel.linear_idx_type, element_size=kernel.element_size], strides: TileTensor[strides_type, Storage=strides.Storage, address_space=strides.address_space, linear_idx_type=strides.linear_idx_type, element_size=strides.element_size], dilations: TileTensor[dilations_type, Storage=dilations.Storage, address_space=dilations.address_space, linear_idx_type=dilations.linear_idx_type, element_size=dilations.element_size], pads: TileTensor[pads_type, Storage=pads.Storage, address_space=pads.address_space, linear_idx_type=pads.linear_idx_type, element_size=pads.element_size], output_pads: TileTensor[output_pads_type, Storage=output_pads.Storage, address_space=output_pads.address_space, linear_idx_type=output_pads.linear_idx_type, element_size=output_pads.element_size]) -> IndexList[input.LayoutType.rank]

Compute the output shape of a conv-transpose operation, and assert the inputs are compatible.

Parameters:

dtype (DType): Element type of the input and kernel tensor.
strides_type (DType): Element type of the strides tensor.
dilations_type (DType): Element type of the dilations tensor.
pads_type (DType): Element type of the pads tensor.
output_pads_type (DType): Element type of the output_pads tensor.

Args:

input (TileTensor[dtype, Storage=input.Storage, address_space=input.address_space, linear_idx_type=input.linear_idx_type, element_size=input.element_size]): The input tensor.
kernel (TileTensor[dtype, Storage=kernel.Storage, address_space=kernel.address_space, linear_idx_type=kernel.linear_idx_type, element_size=kernel.element_size]): The kernel tensor.
strides (TileTensor[strides_type, Storage=strides.Storage, address_space=strides.address_space, linear_idx_type=strides.linear_idx_type, element_size=strides.element_size]): The strides tensor.
dilations (TileTensor[dilations_type, Storage=dilations.Storage, address_space=dilations.address_space, linear_idx_type=dilations.linear_idx_type, element_size=dilations.element_size]): The dilations tensor.
pads (TileTensor[pads_type, Storage=pads.Storage, address_space=pads.address_space, linear_idx_type=pads.linear_idx_type, element_size=pads.element_size]): The paddings tensor.
output_pads (TileTensor[output_pads_type, Storage=output_pads.Storage, address_space=output_pads.address_space, linear_idx_type=output_pads.linear_idx_type, element_size=output_pads.element_size]): The output paddings tensor.

Returns:

IndexList[input.LayoutType.rank]: The output shape.