Function Differences with torch.nn.functional.soft_margin_loss

torch.nn.functional.soft_margin_loss(input, target, size_average=None, reduce=None, reduction='mean')  -> Tensor/Scalar

class mindspore.nn.SoftMarginLoss(reduction='mean')(logits, labels)  -> Tensor

# PyTorch
import torch
from torch import tensor
import torch.nn as nn

logits = torch.FloatTensor([[0.3, 0.7], [0.5, 0.5]])
labels = torch.FloatTensor([[-1, 1], [1, -1]])
output = torch.nn.functional.soft_margin_loss(logits, labels)
print(output.numpy())
# 0.6764238

# MindSpore
import mindspore
import numpy as np
from mindspore import Tensor

loss = mindspore.nn.SoftMarginLoss()
logits = Tensor(np.array([[0.3, 0.7], [0.5, 0.5]]), mindspore.float32)
labels = Tensor(np.array([[-1, 1], [1, -1]]), mindspore.float32)
output = loss(logits, labels)
print(output)
# 0.6764238