Class AdaptiveMaxPool2dImpl¶
Defined in File pooling.h
Page Contents
Inheritance Relationships¶
Base Type¶
public torch::nn::AdaptiveMaxPoolImpl< 2, ExpandingArrayWithOptionalElem< 2 >, AdaptiveMaxPool2dImpl >(Template Class AdaptiveMaxPoolImpl)
Class Documentation¶
-
class AdaptiveMaxPool2dImpl : public torch::nn::AdaptiveMaxPoolImpl<2, ExpandingArrayWithOptionalElem<2>, AdaptiveMaxPool2dImpl>¶
Applies adaptive maxpool over a 2-D input.
See https://pytorch.org/docs/main/nn.html#torch.nn.AdaptiveMaxPool2d to learn about the exact behavior of this module.
See the documentation for
torch::nn::AdaptiveMaxPool2dOptionsclass to learn what constructor arguments are supported for this module.Example:
AdaptiveMaxPool2d model(AdaptiveMaxPool2dOptions({3, 2}));
Public Functions
-
Tensor forward(const Tensor &input)¶
-
std::tuple<Tensor, Tensor> forward_with_indices(const Tensor &input)¶
Returns the indices along with the outputs.
Useful to pass to nn.MaxUnpool2d.
-
Tensor forward(const Tensor &input)¶
