mindspore.ops.adaptive_avg_pool3d

mindspore.ops.adaptive_avg_pool3d(input, output_size)[source]

Performs 3D adaptive average pooling on a multi-plane input signal. 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 x is $(i n D, i n H, i n W)$ , the last 3 dimension size of output is $(o u t D, o u t H, o u t W)$ .

\begin{array}{r} \begin{array}{ll} \forall o d \in [0, o u t D - 1], o h \in [0, o u t H - 1], o w \in [0, o u t W - 1] \\ o u t p u t [o d, o h, o w] = \\ m e a n (x [i s t a r t D : i e n d D + 1, i s t a r t H : i e n d H + 1, i s t a r t W : i e n d W + 1]) \\ w h e r e, \\ i s t a r t D = ⌈ \frac{o d * i n D}{o u t D} ⌉ \\ i e n d D = ⌊ \frac{(o d + 1) * i n D}{o u t D} ⌋ \\ i s t a r t H = ⌈ \frac{o h * i n H}{o u t H} ⌉ \\ i e n d H = ⌊ \frac{(o h + 1) * i n H}{o u t H} ⌋ \\ i s t a r t W = ⌈ \frac{o w * i n W}{o u t W} ⌉ \\ i e n d W = ⌊ \frac{(o w + 1) * i n W}{o u t W} ⌋ \end{array} \end{array}

Parameters

input (Tensor) – The input of adaptive_avg_pool3d, which is a 5D or 4D Tensor.
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.

Returns

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
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> # case 1: output_size=(3, 3, 4)
>>> output_size=(3, 3, 4)
>>> input_val = np.random.randn(4, 3, 5, 6, 7)
>>> input = Tensor(input_val, mindspore.float32)
>>> output = ops.adaptive_avg_pool3d(input, output_size)
>>> print(output.shape)
(4, 3, 3, 3, 4)
>>> # case 2: output_size=4
>>> output_size=5
>>> input_val = np.random.randn(2, 3, 8, 6, 12)
>>> input = Tensor(input_val, mindspore.float32)
>>> output = ops.adaptive_avg_pool3d(input, output_size)
>>> print(output.shape)
(2, 3, 5, 5, 5)
>>> # case 3: output_size=(None, 4, 5)
>>> output_size=(None, 4, 5)
>>> input_val = np.random.randn(4, 1, 9, 10, 8)
>>> input = Tensor(input_val, mindspore.float32)
>>> output = ops.adaptive_avg_pool3d(input, output_size)
>>> print(output.shape)
(4, 1, 9, 4, 5)