如何在 Pytorch 中迭代图层

Question

假设我有一个名为m 的网络模型对象。现在我没有关于这个网络有多少层的先验信息。如何创建一个 for 循环来迭代其层？ 我正在寻找类似的东西：

Weight=[]
for layer in m._modules:
    Weight.append(layer.weight)

Answer 1

假设您有以下神经网络。

import torch
import torch.nn as nn
import torch.nn.functional as F

class Net(nn.Module):

    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.conv2 = nn.Conv2d(6, 16, 5)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        # define the forward function 
        return x

现在，让我们打印与每个 NN 层相关的权重参数的大小。

model = Net()
for name, param in model.named_parameters():
    print(name, param.size())

输出：

conv1.weight torch.Size([6, 1, 5, 5])
conv1.bias torch.Size([6])
conv2.weight torch.Size([16, 6, 5, 5])
conv2.bias torch.Size([16])
fc1.weight torch.Size([120, 400])
fc1.bias torch.Size([120])
fc2.weight torch.Size([84, 120])
fc2.bias torch.Size([84])
fc3.weight torch.Size([10, 84])
fc3.bias torch.Size([10])

希望您可以扩展示例以满足您的需求。

Answer 2

假设 m 是你的模块，那么你可以这样做：

for layer in m.children():
    weights = list(layer.parameters())

Answer 3

您可以使用children 方法：

for module in model.children():
    # ...

或者，如果你想flatten Sequential layers：

for module in model.modules():
    if not isinstance(module, nn.Sequential):
        # ...

Answer 4

您可以使用model.named_parameters() 简单地获取它，这将返回一个生成器，您可以对其进行迭代并获取张量、其名称等。

这是 resnet 预训练模型的代码：

In [106]: resnet = torchvision.models.resnet101(pretrained=True)

In [107]: for name, param in resnet.named_parameters(): 
     ...:     print(name, param.shape) 

会输出

conv1.weight torch.Size([64, 3, 7, 7])
bn1.weight torch.Size([64])
bn1.bias torch.Size([64])
layer1.0.conv1.weight torch.Size([64, 64, 1, 1])
layer1.0.bn1.weight torch.Size([64])
layer1.0.bn1.bias torch.Size([64])
........
........ and so on

你可以在how-to-manipulate-layer-parameters-by-its-names/找到一些关于这个话题的讨论

Answer 5

你也可以这样做：

for name, m in mdl.named_children():
    print(name)
    print(m.parameters())

---

参考：

# https://discuss.pytorch.org/t/how-to-get-the-module-names-of-nn-sequential/39682
# looping through modules but get the one with a specific name

import torch
import torch.nn as nn

from collections import OrderedDict

params = OrderedDict([
    ('fc0', nn.Linear(in_features=4,out_features=4)),
    ('ReLU0', nn.ReLU()),
    ('fc1L:final', nn.Linear(in_features=4,out_features=1))
])
mdl = nn.Sequential(params)

# throws error
# mdl['fc0']

for m in mdl.children():
    print(m)

print()

for m in mdl.modules():
    print(m)

print()

for name, m in mdl.named_modules():
    print(name)
    print(m)

print()

for name, m in mdl.named_children():
    print(name)
    print(m)