Question

我想在fc1和fc2层之间添加一个torch.nn.ReLU()层。

原始代码：

型号：

# ...
self.fc1 = nn.Linear(4096, 256)
self.fc2 = nn.Linear(256, 4096)
# ...

def forward(...):
    # ...
    x = x.view(-1, 4096)
    x = self.fc1(x))
    if a7 is not None:
        x = x * a7.squeeze()
    # ...

我尝试了

# ...
x = x.view(-1, 4096)
x = nn.ReLU(self.fc1(x)))
if a7 is not None:
    x = x * a7.squeeze()
# ...

此错误弹出。

Answer 1

我的回答假设__init__是一个错字，应该是forward。如果不是这种情况，请告诉我，我将其删除。

import torch
from torch import nn

class SimpleModel(nn.Module):
  def __init__(self, with_relu=False):
    super(SimpleModel, self).__init__()
    self.fc1 = nn.Sequential(nn.Linear(3, 10), nn.ReLU(inplace=True)) if with_relu else nn.Linear(3, 10)
    self.fc2 = nn.Linear(10, 3)

  def forward(self, x):
    x = self.fc1(x)
    print(torch.min(x))  # just to show you ReLU is working...
    return self.fc2(x)

# Model without ReLU
net_without_relu = SimpleModel(with_relu=False)
print(net_without_relu)

# Model with ReLU
net_with_relu = SimpleModel(with_relu=True)
print(net_with_relu)

# random input data
x = torch.randn((5, 3))
print(x)

# we expect it to print something < 0
output1 = net_without_relu(x)

# we expect it to print 0.
output2 = net_with_relu(x)

您可以检查下面在Colab上运行的代码：https://colab.research.google.com/drive/1W3Dh4_KPd3iABx5FSzZm3tilm6tnJh0v

要按尝试使用：

x = nn.ReLU(self.fc1(x)))

您可以使用功能性API：

from torch.nn import functional as F

# ...
x = F.relu(self.fc1(x)))

Answer 2

您不应在__init__中执行任何查看方法。初始化应保持您的结构。例如，这是从AlexNet __init__

复制而来的

nn.Linear(4096, 4096),
nn.ReLU(inplace=True),
nn.Linear(4096, num_classes),

但是，您的前进方法可能包含重塑，计算和功能。

nn.Sequential应该是__init__的一部分，就像在AlexNet中一样：

class AlexNet(nn.Module):

    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(192, 384, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.Conv2d(256, 256, kernel_size=3, padding=1),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
        )
        self.classifier = nn.Sequential(
            nn.Dropout(),
            nn.Linear(256 * 6 * 6, 4096),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(4096, 4096),
            nn.ReLU(inplace=True),
            nn.Linear(4096, num_classes),
        )

    def forward(self, x):
        x = self.features(x)
        x = x.view(x.size(0), 256 * 6 * 6)
        x = self.classifier(x)
        return x

然后您可以向前使用类属性self.features，self.classifier。

_{注意：这是来自PyTorch 0.4的AlexNet的旧模型，但它相当简单，逻辑相同}

TypeError：mul（）参数'other'（位置1）必须为Tensor，而不是ReLU

2 个答案: