ёiCSSKJr SSKJr SSKJr SSKJr \(aSSK J r SSK J r J r Jr SSKJr "S S \5rg ) ) annotations) TYPE_CHECKING)Layer) functional)Tensor) DataLayout3DSize3Size6)_PaddingSizeModec^\rSrSr%SrS\S'S\S'S\S'S \S 'S \S 'S \S 'S\S'SSU4SjjjrSSjrSSjrSr U=r $) MaxPool3D!a This operation applies 3D max pooling over input features based on the sparse input, and kernel_size, stride, padding parameters. Input(X) and Output(Out) are in NDHWC format, where N is batch size, C is the number of channels, H is the height of the feature, D is the depth of the feature, and W is the width of the feature. 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, optional): 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. Default None, then stride will be equal to the kernel_size. padding(str|int|list|tuple, optional): 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 . [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, optional): ${ceil_mode_comment} return_mask(bool, optional): Whether to return the max indices along with the outputs. data_format(str, optional): The data format of the input and output data. An optional string from: `"NCDHW"`, `"NDHWC"`. The default is `"NCDHW"`. When it is `"NCDHW"`, the data is stored in the order of: `[batch_size, input_channels, input_depth, input_height, input_width]`. Currently, only support "NDHWC". name(str, optional): For detailed information, please refer to :ref:`api_guide_Name`. Usually name is no need to set and None by default. Returns: A callable object of MaxPool3D. Shape: - x(Tensor): The input SparseCooTensor of max pool3d operator, which is a 5-D tensor. The data type can be float32, float64. - output(Tensor): The output tensor of max pool3d operator, which is a 5-D tensor. The data type is same as input x. Examples: .. code-block:: pycon >>> import paddle >>> dense_x = paddle.randn((2, 3, 6, 6, 3)) >>> sparse_x = dense_x.to_sparse_coo(4) >>> max_pool3d = paddle.sparse.nn.MaxPool3D(kernel_size=3, data_format='NDHWC') >>> out = max_pool3d(sparse_x) >>> print(out.shape) paddle.Size([2, 1, 2, 2, 3]) r kernel_size Size3 | Nonestride _PaddingSizeMode | Size3 | Size6paddingbool return_mask ceil_moder data_format str | Nonenamecv>[TU]5 XlX lX0lX@lXPlX`lXplg)N) super__init__ksizerrrrrr) selfrrrrrrr __class__s ^/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/sparse/nn/layer/pooling.pyrMaxPool3D.__init___s5    &"& c [R"UURURURUR UR URS9$)N)rrrrrr)F max_pool3drrrrrr)rxs r!forwardMaxPool3D.forwardrsB||  ;;LLnn((  r#c:SR"S0URD6$)Nz7kernel_size={ksize}, stride={stride}, padding={padding})format__dict__)rs r! extra_reprMaxPool3D.extra_repr}s!HOO mm  r#)rrrrrrr)NrFFNDHWCN)rr rrrrrrrrrr rrreturnNone)r'rr1r)r1str) __name__ __module__ __qualname____firstlineno____doc____annotations__rr(r.__static_attributes__ __classcell__)r s@r!rr!s3j  --O  $45!$+2     " &    r#rN) __future__rtypingr paddle.nnrrr%paddlerpaddle._typingr r r paddle.nn.functional.commonr rr+r#r!rCs6#  =_ _ r#