ϑim(NSSKJr SSKJr SSKJr SSKJr SSKJ r SSK J r SSK J r \(aSSKJr /r\ "S S S S S 9SSSjj5r\ "S SS SS 9SSSjj5r\ "S SS SS 9SSSjj5r\ "S SS SS 9SSSjj5rg)) annotations) TYPE_CHECKING)_C_ops)check_variable_and_dtype) LayerHelper)in_dynamic_or_pir_mode) deprecated)Tensorz2.4.0zpaddle.geometric.segment_sumz5paddle.incubate.segment_sum will be removed in future)since update_tolevelreasonNcD[5(a[R"XS5$[USSS5 [USSS5 [ S 0[ 5D6nUR URS9nUR URS9nURSXS.XES .S S0S 9 U$) a Segment Sum Operator. Sum the elements of input `data` which with the same index in `segment_ids`. It computes a tensor such that .. math:: out_i = \sum_{j \in \{segment\_ids_j == i \} } data_{j} where sum is over j such that `segment_ids[j] == i`. Args: data (Tensor): A tensor, available data type float32, float64, int32, int64. segment_ids (Tensor): A 1-D tensor, which have the same size with the first dimension of input data. Available data type is int32, int64. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: Tensor, the Segment Sum result. Examples: .. code-block:: python >>> import paddle >>> data = paddle.to_tensor([[1, 2, 3], [3, 2, 1], [4, 5, 6]], dtype='float32') >>> segment_ids = paddle.to_tensor([0, 0, 1], dtype='int32') >>> out = paddle.incubate.segment_sum(data, segment_ids) >>> print(out) Tensor(shape=[2, 3], dtype=float32, place=Place(cpu), stop_gradient=True, [[4., 4., 4.], [4., 5., 6.]]) SUMXfloat32float64int32int64 segment_pool SegmentIdsrrdtyperrOut SummedIdspooltypetypeinputsoutputsattrs) segment_sum rrrrrlocals"create_variable_for_type_inferencer append_opdata segment_idsnamehelperout summed_idss [/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/incubate/tensor/math.pyr'r's^""4e<< #?  ! '9> 7fh777djj7I>>TZZ>P 99u%   zpaddle.geometric.segment_meanz6paddle.incubate.segment_mean will be removed in futurecD[5(a[R"XS5$[USSS5 [USSS5 [ S 0[ 5D6nUR URS9nUR URS9nURSXS.XES .S S0S 9 U$) a Segment Mean Operator. Ihis operator calculate the mean value of input `data` which with the same index in `segment_ids`. It computes a tensor such that .. math:: out_i = \mathop{mean}_{j \in \{segment\_ids_j == i \} } data_{j} where sum is over j such that 'segment_ids[j] == i' and $n_i$ is the number of all index 'segment_ids[j] == i'. Args: data (tensor): a tensor, available data type float32, float64, int32, int64. segment_ids (tensor): a 1-d tensor, which have the same size with the first dimension of input data. available data type is int32, int64. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: Tensor, the Segment Mean result. Examples: .. code-block:: python >>> import paddle >>> data = paddle.to_tensor([[1, 2, 3], [3, 2, 1], [4, 5, 6]], dtype='float32') >>> segment_ids = paddle.to_tensor([0, 0, 1], dtype='int32') >>> out = paddle.incubate.segment_mean(data, segment_ids) >>> print(out) Tensor(shape=[2, 3], dtype=float32, place=Place(cpu), stop_gradient=True, [[2., 2., 2.], [4., 5., 6.]]) MEANrrrrrrrrr!r") segment_meanr(r,s r3r7r7dsb""4f== c;^\#5~ 468 4F  3 3$** 3 EC:::LJ  556"  Jr4zpaddle.geometric.segment_minz5paddle.incubate.segment_min will be removed in futurecD[5(a[R"XS5$[USSS5 [USSS5 [ S 0[ 5D6nUR URS9nUR URS9nURSXS.XES .S S0S 9 U$) a Segment min operator. Calculate the minimum elements of input `data` which with the same index in `segment_ids`. It computes a tensor such that .. math:: out_i = \min_{j \in \{segment\_ids_j == i \} } data_{j} where min is over j such that `segment_ids[j] == i`. Args: data (tensor): a tensor, available data type float32, float64, int32, int64. segment_ids (tensor): a 1-d tensor, which have the same size with the first dimension of input data. available data type is int32, int64. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: Tensor, the minimum result. Examples: .. code-block:: python >>> import paddle >>> data = paddle.to_tensor([[1, 2, 3], [3, 2, 1], [4, 5, 6]], dtype='float32') >>> segment_ids = paddle.to_tensor([0, 0, 1], dtype='int32') >>> out = paddle.incubate.segment_min(data, segment_ids) >>> print(out) Tensor(shape=[2, 3], dtype=float32, place=Place(cpu), stop_gradient=True, [[1., 2., 1.], [4., 5., 6.]]) MINrrrrrrrrr!r") segment_minr(r,s r3r:r:s`""4e<< c;^\#5~ 3&( 3F  3 3$** 3 EC:::LJ  555!  Jr4zpaddle.geometric.segment_maxz5paddle.incubate.segment_max will be removed in futurecH[5(a[R"XS5nU$[USSS5 [USSS5 [ S 0[ 5D6nUR URS9nUR URS9nURSXS.X5S .S S0S 9 U$) a Segment max operator. Calculate the maximum elements of input `data` which with the same index in `segment_ids`. It computes a tensor such that .. math:: out_i = \max_{j \in \{segment\_ids_j == i \} } data_{j} where max is over j such that `segment_ids[j] == i`. Args: data (tensor): a tensor, available data type float32, float64, int32, int64. segment_ids (tensor): a 1-d tensor, which have the same size with the first dimension of input data. available data type is int32, int64. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: Tensor, the maximum result. Examples: .. code-block:: python >>> import paddle >>> data = paddle.to_tensor([[1, 2, 3], [3, 2, 1], [4, 5, 6]], dtype='float32') >>> segment_ids = paddle.to_tensor([0, 0, 1], dtype='int32') >>> out = paddle.incubate.segment_max(data, segment_ids) >>> print(out) Tensor(shape=[2, 3], dtype=float32, place=Place(cpu), stop_gradient=True, [[3., 2., 3.], [4., 5., 6.]]) MAXrrrrrrrrr!r") segment_maxr()r-r.r/r1r0r2s r3r=r=s`!!$U;  c;^\#5~ 3&( 3F  3 3$** 3 EC:::LJ  555!  Jr4)N)r-r r.r r/z str | Nonereturnr ) __future__rtypingrpaddlerpaddle.base.data_feederrpaddle.base.layer_helperrpaddle.frameworkr paddle.utilsr r __all__r'r7r:r=r4r3rHsR# <03#  , B ;?< <%<-7< <  <~ - C ;?> >%>-7> >  >B , B ;?= =%=-7= =  =@ , B ;?> >%>-7> >  >r4