\;j+ <ddlmZddlmZddlmZddlmZddZy)) _legacy_C_ops)check_variable_and_dtype) LayerHelper)in_dynamic_modect|tr0ddddj|j}| t dt rt j|d|St|ddd gd d|i}tdit}|jd }|j|}|jd d |id |i||S)aMarks a tensor as being part of the loss calculation for IPU. This operator is used to handle on the (final) loss of a model so that it is used as the start of backpropagation. When `reduction` is `none`, return raw `Out`. When `reduction` is `mean`, return .. math:: Out = MEAN(Out) When `reduction` is `sum`, return .. math:: Out = SUM(Out) Parameters: x (Variable): The input tensor. The shapes is [N, *], where N is batch size and `*` means any number of additional dimensions. It's data type should be float32, float64 on CPU and float16, float32 on IPU. reduction(str|int, optional): Reduce the loss output. Supported string values are: 'sum', 'mean', 'none' the corresponding int values are 0, 1, 2 respectively. The default value is "none". Returns: Variable: The loss ``Tensor`` with the specified reduction applied. Examples: .. code-block:: python >>> import paddle >>> paddle.enable_static() >>> loss = paddle.static.data(name="loss", shape=[-1, 1], dtype="float32") >>> out = paddle.incubate.identity_loss(loss, reduction=1) r)summeannonezUnsupported reduction type. reductionxfloat32float64 identity_loss)input_param_nameXOut)typeinputsoutputsattrs)r) isinstancestrgetlower Exceptionrrrrrlocals input_dtype"create_variable_for_type_inference append_op)rr rhelperdtypeouts `G:\00. PROJECTS\API\Inventory\templateJSON\kerjaOCR\Lib\site-packages\paddle/incubate/nn/loss.pyrrsH)S!q!4889JK  9: :**1k9EEQi%;_M ) $E  5FH 5F     4E  3 3E :C  c1Xs|5 JN)r ) paddlerpaddle.base.data_feederrpaddle.base.layer_helperrpaddle.frameworkrrr&r%r,s!<0,4r&