PyTorch：损失函数loss function

Posted 2022-12-09 -柚子皮-

-柚子皮-

Loss Functions

nn.L1Loss	Creates a criterion that measures the mean absolute error (MAE) between each element in the input xx and target yy .
nn.MSELoss	Creates a criterion that measures the mean squared error (squared L2 norm) between each element in the input xx and target yy .
nn.CrossEntropyLoss	This criterion combines nn.LogSoftmax() and nn.NLLLoss() in one single class.
nn.CTCLoss	The Connectionist Temporal Classification loss.
nn.NLLLoss	The negative log likelihood loss.
nn.PoissonNLLLoss	Negative log likelihood loss with Poisson distribution of target.
nn.KLDivLoss	The Kullback-Leibler divergence loss measure
nn.BCELoss	Creates a criterion that measures the Binary Cross Entropy between the target and the output:
nn.BCEWithLogitsLoss	This loss combines a Sigmoid layer and the BCELoss in one single class.
nn.MarginRankingLoss	Creates a criterion that measures the loss given inputs x1x1 , x2x2 , two 1D mini-batch Tensors, and a label 1D mini-batch tensor yy (containing 1 or -1).
nn.HingeEmbeddingLoss	Measures the loss given an input tensor xx and a labels tensor yy (containing 1 or -1).
nn.MultiLabelMarginLoss	Creates a criterion that optimizes a multi-class multi-classification hinge loss (margin-based loss) between input xx (a 2D mini-batch Tensor) and output yy (which is a 2D Tensor of target class indices).
nn.SmoothL1Loss	Creates a criterion that uses a squared term if the absolute element-wise error falls below beta and an L1 term otherwise.
nn.SoftMarginLoss	Creates a criterion that optimizes a two-class classification logistic loss between input tensor xx and target tensor yy (containing 1 or -1).
nn.MultiLabelSoftMarginLoss	Creates a criterion that optimizes a multi-label one-versus-all loss based on max-entropy, between input xx and target yy of size (N, C)(N,C) .
nn.CosineEmbeddingLoss	Creates a criterion that measures the loss given input tensors x_1x1​ , x_2x2​ and a Tensor label yy with values 1 or -1.
nn.MultiMarginLoss	Creates a criterion that optimizes a multi-class classification hinge loss (margin-based loss) between input xx (a 2D mini-batch Tensor) and output yy (which is a 1D tensor of target class indices, 0 \\leq y \\leq \\textx.size(1)-10≤y≤x.size(1)−1 ):
nn.TripletMarginLoss	Creates a criterion that measures the triplet loss given an input tensors x1x1 , x2x2 , x3x3 and a margin with a value greater than 00 .
nn.TripletMarginWithDistanceLoss	Creates a criterion that measures the triplet loss given input tensors aa , pp , and nn (representing anchor, positive, and negative examples, respectively), and a nonnegative, real-valued function (“distance function”) used to compute the relationship between the anchor and positive example (“positive distance”) and the anchor and negative example (“negative distance”).

参数

reduction (string, optional) – Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'. 'none': no reduction will be applied, 'mean': the weighted mean of the output is taken, 'sum': the output will be summed. Note: size_average and reduce are in the process of being deprecated, and in the meantime, specifying either of those two args will override reduction. Default: 'mean'

[CROSSENTROPYLOSS]

[pytorch loss function 总结]

示例：

import torch.nn.functional as F

labels = dataloader["label"]
predictions = outputs.squeeze().contiguous()

loss = F.binary_cross_entropy(predictions, labels, reduction='mean')

from: -柚子皮-

ref: [https://pytorch.org/docs/stable/nn.html#loss-functions]