Function Differences with torch.nn.SmoothL1Loss

class torch.nn.SmoothL1Loss(size_average=None, reduce=None, reduction='mean', beta=1.0)(input, target) -> Tensor

class mindspore.nn.SmoothL1Loss(beta=1.0, reduction='none')(logits, labels) -> Tensor

# PyTorch
import torch
import torch.nn as nn

beta = 1
loss = nn.SmoothL1Loss(reduction="none", beta=beta)
logits = torch.FloatTensor([1, 2, 3])
labels = torch.FloatTensor([1, 2, 2])
output = loss(logits, labels)
print(output.numpy())
# [0.  0.  0.5]

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

loss = mindspore.nn.SmoothL1Loss()
logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
labels = Tensor(np.array([1, 2, 2]), mindspore.float32)
output = loss(logits, labels)
print(output)
# [0.  0.  0.5]