Machine learning pytorch问题:如何添加偏差项并提取其值?类与序列模型?和softmax
我在pytorch中有一个基本的神经网络模型,如下所示:Machine learning pytorch问题:如何添加偏差项并提取其值?类与序列模型?和softmax,machine-learning,deep-learning,pytorch,torch,Machine Learning,Deep Learning,Pytorch,Torch,我在pytorch中有一个基本的神经网络模型,如下所示: import torch import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self, input_dim, hidden_dim, output_dim): super(Net, self).__init__() self.fc1 = nn.Linear(input_d
import torch
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self, input_dim, hidden_dim, output_dim):
super(Net, self).__init__()
self.fc1 = nn.Linear(input_dim, hidden_dim)
self.sigmoid = nn.Sigmoid()
self.fc2 = nn.Linear(hidden_dim, output_dim)
def forward(self, x):
out = self.fc1(x)
out = self.sigmoid(out)
out = self.fc2(out)
return out
net = Net(400, 512,10)
如何从net.parameters()中提取偏差/截距项?
这个模型等同于使用sequential()吗
对于多类分类,在两种模型的末尾nn.Softmax()是可选的吗?如果我理解正确的话,有了软件,它会输出某个类的概率,但没有它,它会返回预测的输出吗
提前感谢您回答我的新手问题。您可以声明模型中每个层或函数的提取偏差 您网络中的两个存在是相同的,但是如果您想扩展netwrok,我建议使用Net one而不是Sequential one 如果没有softmax,它只会输出一个最小值为-1最大值为1的张量,如果使用sigmoid,则无法预测
无论如何,你应该分开回答你的问题,而不是一篇文章回答三个问题。祝你好运,让我们逐一回答问题
此模型是否等同于使用sequential()
简短回答:没有。您可以看到您添加了两个S形和两个线性层。您可以打印网络并查看结果:
net = Net(400, 512,10)
print(net.parameters())
print(net)
input_dim = 400
hidden_dim = 512
output_dim = 10
model = Net(400, 512,10)
net = nn.Sequential(nn.Linear(input_dim, hidden_dim),
nn.Sigmoid(),
nn.Linear(hidden_dim, hidden_dim),
nn.Sigmoid(),
nn.Linear(hidden_dim, output_dim))
print(net)
输出为:
Net(
(fc1): Linear(in_features=400, out_features=512, bias=True)
(sigmoid): Sigmoid()
(fc2): Linear(in_features=512, out_features=10, bias=True)
)
Sequential(
(0): Linear(in_features=400, out_features=512, bias=True)
(1): Sigmoid()
(2): Linear(in_features=512, out_features=512, bias=True)
(3): Sigmoid()
(4): Linear(in_features=512, out_features=10, bias=True)
)
tensor([ 3.4078e-02, 3.1537e-02, 3.0819e-02, 2.6163e-03, 2.1002e-03,
4.6842e-05, -1.6454e-02, -2.9456e-02, 2.0646e-02, -3.7626e-02,
3.5531e-02, 4.7748e-02, -4.6566e-02, -1.3317e-02, -4.6593e-02,
-8.9996e-03, -2.6568e-02, -2.8191e-02, -1.9806e-02, 4.9720e-02,
---------------------------------------------------------------
-4.6214e-02, -3.2799e-02, -3.3605e-02, -4.9720e-02, -1.0293e-02,
3.2559e-03, -6.6590e-03, -1.2456e-02, -4.4547e-02, 4.2101e-02,
-2.4981e-02, -3.6840e-03], requires_grad=True)
我希望你能看到他们的不同之处
您的第一个问题:如何从net.parameters()中提取偏差/截距项
答案是:
model = Net(400, 512,10)
bias = model.fc1.bias
print(bias)
输出为:
Net(
(fc1): Linear(in_features=400, out_features=512, bias=True)
(sigmoid): Sigmoid()
(fc2): Linear(in_features=512, out_features=10, bias=True)
)
Sequential(
(0): Linear(in_features=400, out_features=512, bias=True)
(1): Sigmoid()
(2): Linear(in_features=512, out_features=512, bias=True)
(3): Sigmoid()
(4): Linear(in_features=512, out_features=10, bias=True)
)
tensor([ 3.4078e-02, 3.1537e-02, 3.0819e-02, 2.6163e-03, 2.1002e-03,
4.6842e-05, -1.6454e-02, -2.9456e-02, 2.0646e-02, -3.7626e-02,
3.5531e-02, 4.7748e-02, -4.6566e-02, -1.3317e-02, -4.6593e-02,
-8.9996e-03, -2.6568e-02, -2.8191e-02, -1.9806e-02, 4.9720e-02,
---------------------------------------------------------------
-4.6214e-02, -3.2799e-02, -3.3605e-02, -4.9720e-02, -1.0293e-02,
3.2559e-03, -6.6590e-03, -1.2456e-02, -4.4547e-02, 4.2101e-02,
-2.4981e-02, -3.6840e-03], requires_grad=True)
谢谢你的回答。如果我在类中添加另一个sigmoid。这是不是也一样?我的意思是,如果有相同数量的隐藏节点/层和相同的激活函数设置,那么nn.sequential()和类Net(nn.Module)在功能上是否做了相同的事情?是的,这是正确的。如果在sequential和自定义的Net(nn.Module)类中添加相同的层,则它们具有相同的网络体系结构。