mindspore.ops.AdaptiveAvgPool2D

class mindspore.ops.AdaptiveAvgPool2D(output_size)[源代码]

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.

The input and output data format can be “NCHW” and “CHW”. N is the batch size, C is the number of channels, H is the feature height, and W is the feature width.

For avg adaptive pool2d:

\[\begin{split}\begin{align} h_{start} &= floor(i * H_{in} / H_{out})\\ h_{end} &= ceil((i + 1) * H_{in} / H_{out})\\ w_{start} &= floor(j * W_{in} / W_{out})\\ w_{end} &= ceil((j + 1) * W_{in} / W_{out})\\ Output(i,j) &= \frac{\sum Input[h_{start}:h_{end}, w_{start}:w_{end}]}{(h_{end}- h_{start}) * (w_{end}- w_{start})} \end{align}\end{split}\]

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 or 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.

\[\begin{split}out\_shape = \begin{cases} input\_x\_shape[-2] + output\_size[1], & \text{if output_size is (None, w);}\\ output\_size[0] + input\_x\_shape[-1], & \text{if output_size is (h, None);}\\ input\_x\_shape[-2:], & \text{if output_size is (None, None);}\\ (h, h), & \text{if output_size is h;}\\ (h, w), & \text{if output_size is (h, w)} \end{cases}\end{split}\]

Raises

ValueError – If output_size is a tuple and the length of output_size is not 2.
TypeError – If input_x is not a tensor.
TypeError – If dtype of input_x is not float16, float32 nor float64.
ValueError – If the dimension of input_x is less than or equal to the dimension of output_size.

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]]]