比较与torch.nn.functional.dropout3d的差异

torch.nn.functional.dropout3d

torch.nn.functional.dropout3d(input, p=0.5, training=True, inplace=False) -> Tensor

更多内容详见torch.nn.functional.dropout3d。

mindspore.ops.dropout3d

mindspore.ops.dropout3d(input, p=0.5, training=True) -> Tensor

更多内容详见mindspore.ops.dropout3d。

差异对比

MindSpore此API功能与PyTorchy一致，参数支持的数据类型有差异。

PyTorch：在训练期间，dropout3d以服从伯努利分布的概率p随机将输入Tensor的某些通道归零，每个通道将会独立依据伯努利分布概率p来确定是否被清零。对输入Tensor的某些通道清零，已被证明能有效地减少过度拟合，防止神经元共适应。

MindSpore：MindSpore只支持秩为5的Tensor作为输入。

分类	子类	PyTorch	MindSpore	差异
参数	参数1	input	input	MindSpore只支持秩为5的Tensor作为输入
	参数2	p	p	-
	参数3	training	training	-
	参数4	inplace	-	-

代码示例1

# PyTorch
import torch

input = torch.ones(2, 3, 2, 4)
output = torch.nn.functional.dropout3d(input)
print(output.shape)
# torch.Size([2, 3, 2, 4])

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

input = Tensor(np.ones([2, 3, 2, 4]), ms.float32)
input = input.expand_dims(0)
output = ops.dropout3d(input)
output = output.squeeze(0)
print(output.shape)
# (2, 3, 2, 4)

代码示例2

# PyTorch
import torch

input = torch.ones(1, 1, 2, 3, 2, 4)
output = torch.nn.functional.dropout3d(input)
print(output.shape)
# torch.Size([1, 1, 2, 3, 2, 4])

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

input = Tensor(np.ones([1, 1, 2, 3, 2, 4]), ms.float32)
input = input.squeeze(0)
output = ops.dropout3d(input)
output = output.expand_dims(0)
print(output.shape)
# (1, 1, 2, 3, 2, 4)