- paddle.incubate. identity_loss ( x, reduction='none' )
Marks 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\[Out = MEAN(Out)\]
When reduction is sum, return\[Out = SUM(Out)\]
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”.
Tensorwith the specified reduction applied.
- Return type
import paddle paddle.enable_static() loss = paddle.static.data(name="loss", shape=[-1, 1], dtype="float32") out = paddle.incubate.identity_loss(loss, reduction=1)