mindspore.nn.AdaptiveAvgPool3d

View Source On Gitee
class mindspore.nn.AdaptiveAvgPool3d(output_size)[source]

This operator applies a 3D 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 \((D, H, W)\). The number of output features is equal to the number of input planes.

Suppose the last 3 dimension size of input is \((inD, inH, inW)\), then the last 3 dimension size of output is \((outD, outH, outW)\).

\[\begin{split}\begin{array}{ll} \\ \forall \quad od \in [0,outD-1], oh \in [0,outH-1], ow \in [0,outW-1]\\ output[od,oh,ow] = \\ \qquad mean(input[istartD:iendD+1,istartH:iendH+1,istartW:iendW+1])\\ where,\\ \qquad istartD= \left\lceil \frac{od * inD}{outD} \right\rceil \\ \qquad iendD=\left\lfloor \frac{(od+1)* inD}{outD} \right\rfloor \\ \qquad istartH=\left\lceil \frac{oh * inH}{outH} \right\rceil \\ \qquad iendH=\left\lfloor \frac{(oh+1) * inH}{outH} \right\rfloor \\ \qquad istartW=\left\lceil \frac{ow * inW}{outW} \right\rceil \\ \qquad iendW=\left\lfloor \frac{(ow+1) * inW}{outW} \right\rfloor \end{array}\end{split}\]
Parameters

output_size (Union[int, tuple]) – The target output size. output_size can be a tuple \((D, H, W)\), or an int D for \((D, D, D)\). \(D\), \(H\) and \(W\) can be int or None which means the output size is the same as that of the input.

Inputs:

  • input (Tensor) - The input of AdaptiveAvgPool3d, which is a 5D or 4D Tensor, with float16, float32 or float64 data type.

Outputs:

Tensor, with the same type as the input.

Raises

  • TypeError – If input is not a Tensor.

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

  • ValueError – If the dimension of input is not 4D or 5D.

  • ValueError – If output_size value is not positive.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore as ms
>>> import numpy as np
>>> # case 1: output_size=(3, 3, 4)
>>> output_size=(3, 3, 4)
>>> input_x_val = np.random.randn(4, 3, 5, 6, 7)
>>> input_x = ms.Tensor(input_x_val, ms.float32)
>>> net = ms.nn.AdaptiveAvgPool3d(output_size)
>>> output = net(input_x)
>>> print(output.shape)
(4, 3, 3, 3, 4)
>>> # case 2: output_size=4
>>> output_size=5
>>> input_x_val = np.random.randn(2, 3, 8, 6, 12)
>>> input_x = ms.Tensor(input_x_val, ms.float32)
>>> net = ms.nn.AdaptiveAvgPool3d(output_size)
>>> output = net(input_x)
>>> print(output.shape)
(2, 3, 5, 5, 5)
>>> # case 3: output_size=(None, 4, 5)
>>> output_size=(None, 4, 5)
>>> input_x_val = np.random.randn(4, 1, 9, 10, 8)
>>> input_x = ms.Tensor(input_x_val, ms.float32)
>>> net = ms.nn.AdaptiveAvgPool3d(output_size)
>>> output = net(input_x)
>>> print(output.shape)
(4, 1, 9, 4, 5)