mindspore.ops.AdaptiveAvgPool2D

class mindspore.ops.AdaptiveAvgPool2D(output_size)

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:

$$\begin{array}{r}\begin{array}{rl}{h}_{start}& =floor(i\ast H_{in}/H_{out})\\ h_{end}& =ceil((i+1)\ast H_{in}/H_{out})\\ w_{start}& =floor(j\ast W_{in}/W_{out})\\ w_{end}& =ceil((j+1)\ast W_{in}/W_{out})\\ Output(i,j)& =\frac{\sum Input[h_{start}:h_{end},w_{start}:w_{end}]}{(h_{end}-h_{start})\ast (w_{end}-w_{start})}\end{array}\end{array}$$

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.

$$\begin{array}{r}out\mathrm{\_}shape=\{\begin{array}{ll}input\mathrm{\_}x\mathrm{\_}shape[-2]+output\mathrm{\_}size[1],& \text{if output\_size is (None, w);}\\ output\mathrm{\_}size[0]+input\mathrm{\_}x\mathrm{\_}shape[-1],& \text{if output\_size is (h, None);}\\ input\mathrm{\_}x\mathrm{\_}shape[-2:],& \text{if output\_size is (None, None);}\\ (h,h),& \text{if output\_size is h;}\\ (h,w),& \text{if output\_size is (h, w)}\end{array}\end{array}$$

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]]]