[torch 参数更多 ]torch.nn.SmoothL1Loss¶
torch.nn.SmoothL1Loss¶
torch.nn.SmoothL1Loss(size_average=None,
reduce=None,
reduction='mean',
beta=1.0)
paddle.nn.SmoothL1Loss¶
paddle.nn.SmoothL1Loss(reduction='mean',
delta=1.0,
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 |
---|---|---|
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 | 表示应用于输出结果的计算方式。 |
beta | delta | SmoothL1Loss 损失的阈值参数,beta 不为 1.0 时 Paddle 不支持,暂无转写方式。 |
转写示例¶
size_average¶
# Paddle 写法
torch.nn.SmoothL1Loss(size_average=True)
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='mean')
size_average¶
size_average 为 True
# PyTorch 写法
torch.nn.SmoothL1Loss(size_average=True)
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='mean')
size_average 为 False
# PyTorch 写法
torch.nn.SmoothL1Loss(size_average=False)
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='sum')
reduce¶
reduce 为 True
# PyTorch 写法
torch.nn.SmoothL1Loss(reduce=True)
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='mean')
reduce 为 False
# PyTorch 写法
torch.nn.SmoothL1Loss(reduce=False)
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='none')
reduction¶
reduction 为’none’
# PyTorch 写法
torch.nn.SmoothL1Loss(reduction='none')
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='none')
reduction 为’mean’
# PyTorch 写法
torch.nn.SmoothL1Loss(reduction='mean')
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='mean')
reduction 为’sum’
# PyTorch 写法
torch.nn.SmoothL1Loss(reduction='sum')
# Paddle 写法
paddle.nn.SmoothL1Loss(reduction='sum')