多层感知机,其实就是多层神经元。
这一小节比较简单,看一下案例即可。
举例
分类fashion_mnist数据集。
fashion_mnist数据集大小为28*28,我们将28*28=784作为输入,输出为10个分类。
隐藏层一般设置为2^n,此处设置为256.
1.初始化模型参数
import torch
from torch import nn
from d2l import torch as d2l
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = nn.Parameter(torch.randn(
num_inputs, num_hiddens1, requires_grad=True) * 0.01)
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
W2 = nn.Parameter(torch.randn(
num_hiddens, num_outputs, requires_grad=True) * 0.01)
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))
params = [W1, b1, W2, b2]
2.定义激活函数
# 有现成的API,咱们就是不用
def relu(X):
a = torch.zeros_like(X)
return torch.max(X, a)
3.定义模型
# 由于X为28*28,我们把它展平
def net(X):
X = X.reshape((-1, num_inputs))
H = relu(X@W1 + b1) # 这里“@”代表矩阵乘法
return (H@W2 + b2)
4.定义损失函数
# 交叉熵损失,上一节说了
# 报错“grad can be implicitly created only for scalar outputs”
# 把损失函数里面的内容删掉就可以了。该参数主要影响多个样本输入时,损失的综合方法。
# reduction默认为 mean。mean表示损失为多个样本的平均值,sum表示损失的和,none表示不综合。
# loss = nn.CrossEntropyLoss(reduction='none')
loss = nn.CrossEntropyLoss()
5.开始训练
num_epochs, lr = 10, 0.1
updater = torch.optim.SGD(params, lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, updater)
训练的结果:
6.测试
d2l.predict_ch3(net, test_iter)
简洁实现
1.建立模型
import torch
from torch import nn
from d2l import torch as d2l
net = nn.Sequential(nn.Flatten(),
nn.Linear(784, 256),
nn.ReLU(),
nn.Linear(256, 10))
def init_weights(m):
if type(m) == nn.Linear:
nn.init.normal_(m.weight, std=0.01)
net.apply(init_weights);
2.训练
batch_size, lr, num_epochs = 256, 0.1, 10
loss = nn.CrossEntropyLoss()
trainer = torch.optim.SGD(net.parameters(), lr=lr)
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)