max_pool3d

paddle.nn.functional. max_pool3d ( x, kernel_size, stride=None, padding=0, return_mask=False, ceil_mode=False, data_format='NCDHW', name=None ) [source]

This API implements max pooling 2d operation. See more details in api_nn_pooling_MaxPool3d . :param x: The input tensor of pooling operator, which is a 5-D tensor with

System Message: ERROR/3 (/usr/local/lib/python3.8/site-packages/paddle/nn/functional/pooling.py:docstring of paddle.nn.functional.pooling.max_pool3d, line 4)

Unexpected indentation.

shape [N, C, D, H, W]. The format of input tensor is “NCDHW” or “NDHWC”, where N represents batch size, C represents the number of channels, D, H and W represent the depth, height and width of the feature respectively.

System Message: WARNING/2 (/usr/local/lib/python3.8/site-packages/paddle/nn/functional/pooling.py:docstring of paddle.nn.functional.pooling.max_pool3d, line 5)

Block quote ends without a blank line; unexpected unindent.

Parameters
  • kernel_size (int|list|tuple) – The pool kernel size. If the kernel size is a tuple or list, it must contain three integers, (kernel_size_Depth, kernel_size_Height, kernel_size_Width). Otherwise, the pool kernel size will be the cube of an int.

  • stride (int|list|tuple) – The pool stride size. If pool stride size is a tuple or list, it must contain three integers, [stride_Depth, stride_Height, stride_Width). Otherwise, the pool stride size will be a cube of an int.

  • padding (string|int|list|tuple) – The padding size. Padding could be in one of the following forms. 1. A string in [‘valid’, ‘same’]. 2. An int, which means the feature map is zero padded by size of padding on every sides. 3. A list[int] or tuple(int) whose length is 3, [pad_depth, pad_height, pad_weight] whose value means the padding size of each dimension. 4. A list[int] or tuple(int) whose length is 6. [pad_depth_front, pad_depth_back, pad_height_top, pad_height_bottom, pad_width_left, pad_width_right] whose value means the padding size of each side. 5. A list or tuple of pairs of integers. It has the form [[pad_before, pad_after], [pad_before, pad_after], …]. Note that, the batch dimension and channel dimension should be [0,0] or (0,0). The default value is 0.

  • ceil_mode (bool) – ${ceil_mode_comment}

  • return_mask (bool) – Whether to return the max indices along with the outputs. Default False. Only support “NDCHW” data_format.

  • data_format (string) – The data format of the input and output data. An optional string from: “NCDHW”, “NDHWC”. The default is “NCDHW”. When it is “NCDHW”, the data is stored in the order of: [batch_size, input_channels, input_depth, input_height, input_width].

  • name (str, optional) – For detailed information, please refer to Name. Usually name is no need to set and None by default.

Returns

The output tensor of pooling result. The data type is same as input tensor.

Return type

Tensor

Raises
  • ValueError – If padding is a string, but not “SAME” or “VALID”.

  • ValueError – If padding is “VALID”, but ceil_mode is True.

  • ShapeError – If the output’s shape calculated is not greater than 0.

Examples

import paddle
import paddle.nn.functional as F

# max pool3d
x = paddle.uniform([1, 3, 32, 32, 32])
output = F.max_pool3d(x,
                      kernel_size=2,
                      stride=2, padding=0)
# output.shape [1, 3, 16, 16, 16]
# for return_mask=True
x = paddle.uniform([1, 3, 32, 32, 32])
output, max_indices = paddle.nn.functional.max_pool3d(x,
                              kernel_size = 2,
                              stride = 2,
                              padding=0,
                              return_mask=True)
# output.shape [1, 3, 16, 16, 16], max_indices.shape [1, 3, 16, 16, 16]