[ torch 参数更多 ]torch.nn.functional.multilabel_margin_loss

torch.nn.functional.multilabel_margin_loss

torch.nn.functional.multilabel_margin_loss(input, target, size_average=None, reduce=None, reduction='mean')

paddle.nn.functional.multi_label_margin_loss

paddle.nn.functional.multi_label_margin_loss(input, label, reduction='mean', name=None)

PyTorch 相比 Paddle 支持更多其他参数，具体如下：

参数映射

PyTorch PaddlePaddle 备注
input input 输入 Tensor。
target label 标签 Tensor，仅参数名不一致。
size_average - PyTorch 已弃用， Paddle 无此参数，需要转写。
reduce - PyTorch 已弃用， Paddle 无此参数，需要转写。
reduction reduction 指定应用于输出结果的计算方式。

转写示例

size_average

size_average 为 True

# PyTorch 写法
torch.nn.functional.multilabel_margin_loss(size_average=True)

# Paddle 写法
paddle.nn.functional.multi\_label\_margin\_loss(reduction='mean')

size_average 为 False

# PyTorch 写法
torch.nn.functional.multilabel_margin_loss(size_average=False)

# Paddle 写法
paddle.nn.functional.multi\_label\_margin\_loss(reduction='sum')

reduce

reduce 为 True

# PyTorch 写法
torch.nn.functional.multilabel_margin_loss(reduce=True)

# Paddle 写法
paddle.nn.functional.multi\_label\_margin\_loss(reduction='sum')

reduce 为 False

# PyTorch 写法
torch.nn.functional.multilabel_margin_loss(reduce=False)

# Paddle 写法
paddle.nn.functional.multi\_label\_margin\_loss(reduction='none')

reduction

reduction 为'none'

# PyTorch 写法
torch.nn.functional.multilabel_margin_loss(reduction='none')

# Paddle 写法
paddle.nn.functional.multi\_label\_margin\_loss(reduction='none')

reduction 为'mean'

# PyTorch 写法
torch.nn.functional.multilabel_margin_loss(reduction='mean')

# Paddle 写法
paddle.nn.functional.multi\_label\_margin\_loss(reduction='mean')

reduction 为'sum'

# PyTorch 写法
torch.nn.functional.multilabel_margin_loss(reduction='sum')

# Paddle 写法
paddle.nn.functional.multi\_label\_margin\_loss(reduction='sum')