Functional pooling¶
Local pooling supports sum, maximum, and contributor-average reductions.
pool_transpose3d performs contributor averaging on generated fine support
or on an explicit target tensor. The explicit route preserves target coordinate
order and emits zero for unmatched rows.
trilinear_upsample3d uses separable linear weights and normalizes by the
weights present on sparse support. It accepts generated or explicit target
coordinates.
- torch_lattice.nn.functional.pooling.avg_pool3d(inputs, **kwargs)[source]¶
- Return type:
- Parameters:
inputs (SparseTensor)
- torch_lattice.nn.functional.pooling.global_pool(inputs, *, mode='sum', batch_size=None)[source]¶
Reduce sparse features independently for every declared batch.
- Return type:
- Parameters:
inputs (SparseTensor)
mode (Literal['sum', 'avg', 'max'])
batch_size (int | None)
- torch_lattice.nn.functional.pooling.global_sum_pool(inputs, *, batch_size=None)[source]¶
- Return type:
- Parameters:
inputs (SparseTensor)
batch_size (int | None)
- torch_lattice.nn.functional.pooling.global_avg_pool(inputs, *, batch_size=None)[source]¶
- Return type:
- Parameters:
inputs (SparseTensor)
batch_size (int | None)
- torch_lattice.nn.functional.pooling.global_max_pool(inputs, *, batch_size=None)[source]¶
- Return type:
- Parameters:
inputs (SparseTensor)
batch_size (int | None)
- torch_lattice.nn.functional.pooling.max_pool3d(inputs, **kwargs)[source]¶
- Return type:
- Parameters:
inputs (SparseTensor)
- torch_lattice.nn.functional.pooling.pool3d(inputs, *, mode, kernel_size=2, stride=2, padding=0, dilation=1)[source]¶
Local sparse 3D pooling over convolution-style neighborhoods.
- Return type:
- Parameters:
inputs (SparseTensor)
mode (Literal['sum', 'max', 'avg'])
- torch_lattice.nn.functional.pooling.pool_transpose3d(inputs, target=None, *, kernel_size=2, stride=2, padding=0, dilation=1)[source]¶
Average coarse rows onto generated or explicit fine support.
- Return type:
- Parameters:
inputs (SparseTensor)
target (SparseTensor | None)
- torch_lattice.nn.functional.pooling.sum_pool3d(inputs, **kwargs)[source]¶
- Return type:
- Parameters:
inputs (SparseTensor)
- torch_lattice.nn.functional.pooling.trilinear_upsample3d(inputs, target=None, *, stride=2)[source]¶
Upsample sparse features with normalized trilinear interpolation.
- Return type:
- Parameters:
inputs (SparseTensor)
target (SparseTensor | None)