torch.nn.functional.adaptive_max_pool2d

torch.nn.functional.adaptive_max_pool2d(input, output_size, return_indices=False)

对由多个输入平面组成的输入信号应用 2D 自适应最大池化。

See AdaptiveMaxPool2d for details and output shape.

参数

• output_size – the target output size (single integer or double-integer tuple)

• return_indices – whether to return pooling indices. Default: False