感知机是一个二分类模型,求解算法等价于使用批量大小为1的梯度下降。
感知机的缺点:不能解决XOR问题
多层感知机:一次解决不了的问题,可以先学习一个简单函数,再学习一个简单函数,然后用另外一个函数组合两个函数
为什么需要非线性激活函数:如果激活函数是本身,那么输出仍然会是一个线性函数,等价于一个单层的感知机
ReLU优点在于简单
输出是不用激活函数的,激活函数主要是为了避免层数的塌陷,最后一层不需要激活函数。
import torch
from torch import nn
from d2l import torch as d2l
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
'''
# 实现一个具有单隐藏层的多层感知机,它包含256个隐藏单元
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens, requires_grad=True))
print(f'W1.shape: {W1.shape}')
b1 = nn.Parameter(torch.zeros(num_hiddens, requires_grad=True))
print(f'b1.shape: {b1.shape}')
W2 = nn.Parameter(torch.randn(num_hiddens, num_outputs, requires_grad=True))
b2 = nn.Parameter(torch.zeros(num_outputs, requires_grad=True))
params = [W1, b1, W2, b2]
# 实现ReLU激活函数
def relu(X):
a = torch.zeros_like(X)
return torch.max(X, a)
# 实现我们的模型
def net(X):
X = X.reshape((-1, num_inputs))
print(f'X.shape: {X.shape}')
H = relu(X @ W1 + b1)
return (H @ W2 + b2)
loss = nn.CrossEntropyLoss()
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)
'''
# 简洁实现
# 输入是3D的,要Flatten成2D
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)
batch_size, lr, num_epochs = 256, 0.1, 10
loss = nn.CrossEntropyLoss()
trainer = torch.optim.SGD(net.parameters(), lr=lr)
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)