torch / nn / torch.nn
MaxUnpool1d¶
-
class
torch.nn.
MaxUnpool1d
(kernel_size: Union[T, Tuple[T]], stride: Optional[Union[T, Tuple[T]]] = None, padding: Union[T, Tuple[T]] = 0)[source]¶ Computes a partial inverse of
MaxPool1d
.MaxPool1d
is not fully invertible, since the non-maximal values are lost.MaxUnpool1d
takes in as input the output ofMaxPool1d
including the indices of the maximal values and computes a partial inverse in which all non-maximal values are set to zero.Note
MaxPool1d
can map several input sizes to the same output sizes. Hence, the inversion process can get ambiguous. To accommodate this, you can provide the needed output size as an additional argumentoutput_size
in the forward call. See the Inputs and Example below.- Parameters
- Inputs:
input: the input Tensor to invert
indices: the indices given out by
MaxPool1d
output_size (optional): the targeted output size
- Shape:
Input:
Output: , where
or as given by
output_size
in the call operator
Example:
>>> pool = nn.MaxPool1d(2, stride=2, return_indices=True) >>> unpool = nn.MaxUnpool1d(2, stride=2) >>> input = torch.tensor([[[1., 2, 3, 4, 5, 6, 7, 8]]]) >>> output, indices = pool(input) >>> unpool(output, indices) tensor([[[ 0., 2., 0., 4., 0., 6., 0., 8.]]]) >>> # Example showcasing the use of output_size >>> input = torch.tensor([[[1., 2, 3, 4, 5, 6, 7, 8, 9]]]) >>> output, indices = pool(input) >>> unpool(output, indices, output_size=input.size()) tensor([[[ 0., 2., 0., 4., 0., 6., 0., 8., 0.]]]) >>> unpool(output, indices) tensor([[[ 0., 2., 0., 4., 0., 6., 0., 8.]]])
此页内容是否对您有帮助