mindspore.ops.AdaptiveAvgPool2D

class mindspore.ops.AdaptiveAvgPool2D(*args, **kwargs)[source]

AdaptiveAvgPool2D operation.

This operator applies a 2D adaptive average pooling to an input signal composed of multiple input planes. That is, for any input size, the size of the specified output is H x W. The number of output features is equal to the number of input planes.

Parameters

output_size (Union[int, tuple]) – The target output size is H x W. ouput_size can be a tuple, or a single H for H x H, and H and W can be int or None which means the output size is the same as the input.

Inputs:

  • input_x (Tensor) - The input of AdaptiveAvgPool2D, which is a 3D or 4D tensor, with float16, float32, float64 data type.

Outputs:

Tensor, with the same type as the input_x.

Shape of the output is input_x_shape[:len(input_x_shape) - len(out_shape)] + out_shape.

If output_size contains None:

  • out_shape = input_x_shape[-2] + output_size[1]: If output_size is (None, w)

  • out_shape = output_size[0] + input_x_shape[-1]: If output_size is (h, None)

  • out_shape = input_x_shape[-2:]: If output_size is (None, None)

If output_size does not contain None:

  • out_shape = (h, h): If output_size is h

  • out_shape = (h, w): If output_size is (h, w)

Raises

  • ValueError – If output_size is a tuple and if output_size length is not 2.

  • TypeError – If input_x is not a tensor.

  • TypeError – If dtype of input_x is not float16, float32, float64.

  • ValueError – If input_x dimension is less than or equal to output_size dimension.

Supported Platforms:

GPU

Examples

>>> # case 1: output_size=(None, 2)
>>> input_x = Tensor(np.array([[[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]],
>>>                            [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]],
>>>                            [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]]), mindspore.float32)
>>> adaptive_avg_pool_2d = ops.AdaptiveAvgPool2D((None, 2))
>>> output = adaptive_avg_pool_2d(input_x)
>>> print(output)
[[[1.5 2.5]
  [4.5 5.5]
  [7.5 8.5]]
 [[1.5 2.5]
  [4.5 5.5]
  [7.5 8.5]]
 [[1.5 2.5]
  [4.5 5.5]
  [7.5 8.5]]]
>>> # case 2: output_size=2
>>> adaptive_avg_pool_2d = ops.AdaptiveAvgPool2D(2)
>>> output = adaptive_avg_pool_2d(input_x)
>>> print(output)
[[[3. 4.]
  [6. 7.]]
 [[3. 4.]
  [6. 7.]]
 [[3. 4.]
  [6. 7.]]]
>>> # case 3: output_size=(1, 2)
>>> adaptive_avg_pool_2d = ops.AdaptiveAvgPool2D((1, 2))
>>> output = adaptive_avg_pool_2d(input_x)
>>> print(output)
[[[4.5 5.5]]
 [[4.5 5.5]]
 [[4.5 5.5]]]