paddle.nn.functional. nll_loss ( input, label, weight=None, ignore_index=- 100, reduction='mean', name=None ) [source]

This api returns negative log likelihood. See more detail in api_nn_loss_NLLLoss .

  • input (Tensor) – Input tensor, the shape is \([N, C]\), C is the number of classes. But in K-dimension situation, the shape is \([N, C, d_1, d_2, ..., d_K]\). The data type is float32, float64.

  • label (Tensor) – Label tensor, the shape is \([N,]\) or \([N, d_1, d_2, ..., d_K]\). The data type is int64.

  • weight (Tensor, optional) – Weight tensor, a manual rescaling weight given to each class. If given, it has to be a 1D Tensor whose size is [C, ]. Otherwise, it treated as if having all ones. the data type is float32, float64, Default is 'None'.

  • ignore_index (int64, optional) – Specifies a target value that is ignored and does not contribute to the input gradient.

  • reduction (str, optional) – Indicate how to average the loss, the candicates are 'none' | 'mean' | 'sum'. If reduction is 'mean', the reduced mean loss is returned; if reduction is 'sum', the reduced sum loss is returned; if reduction is 'none', no reduction will be apllied. Default is 'mean'.

  • name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.


Tensor, the value of negative log likelihood loss.


import paddle
from paddle.nn.functional import nll_loss
log_softmax = paddle.nn.LogSoftmax(axis=1)

input = paddle.to_tensor([[0.88103855, 0.9908683 , 0.6226845 ],
          [0.53331435, 0.07999352, 0.8549948 ],
          [0.25879037, 0.39530203, 0.698465  ],
          [0.73427284, 0.63575995, 0.18827209],
          [0.05689114, 0.0862954 , 0.6325046 ]], "float32")
log_out = log_softmax(input)
label = paddle.to_tensor([0, 2, 1, 1, 0], "int64")
result = nll_loss(log_out, label)
print(result) # Tensor(shape=[1], dtype=float32, place=CPUPlace, stop_gradient=True, [1.07202101])