多层感知机:
多层感知机在单层神经网络的基础上引入了一到多个隐藏层(hidden layer)。隐藏层位于输入层和输出层之间。
输入和输出个数分别为4和3,中间的隐藏层中包含了5个隐藏单元,输入层不涉及计算,多层感知机的层数为2,隐藏层中的神经元和输入层中各个输入完全连接,输出层中的神经元和隐藏层中的各个神经元也完全连接。因此,多层感知机中的隐藏层和输出层都是全连接层。
多层感知机就是含有至少一个隐藏层的由全连接层组成的神经网络,且每个隐藏层的输出通过激活函数进行变换。多层感知机的层数和各隐藏层中隐藏单元个数都是超参数。
多层感知机按以下方式计算输出:
导入所需模块:
import torch
import numpy as np
import sys
读取数据集:
mnist_train = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=True, download=True, transform=transforms.ToTensor())
mnist_test = torchvision.datasets.FashionMNIST(root='~/Datasets/FashionMNIST', train=False, download=True, transform=transforms.ToTensor())
batch_size = 256
if sys.platform.startswith('win'):
num_workers = 0 # 0表示不用额外的进程来加速读取数据
else:
num_workers = 4
train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers)
test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers)
定义模型的参数:
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = torch.tensor(np.random.normal(0, 0.01, (num_inputs, num_hiddens)), dtype=torch.float)
b1 = torch.zeros(num_hiddens, dtype=torch.float)
W2 = torch.tensor(np.random.normal(0, 0.01, (num_hiddens, num_outputs)), dtype=torch.float)
b2 = torch.zeros(num_outputs, dtype=torch.float)
params = [W1, b1, W2, b2]
for param in params:
param.requires_grad_(requires_grad=True)
定义模型:
def relu(X): # 激活函数
return torch.max(input=X, other=torch.tensor(0.0))
# 使用基础的max函数来实现ReLU,而非直接调用relu函数
def net(X): # 定义模型结构
X = X.view((-1, num_inputs)) # view函数将每张原始图像改成长度为num_inputs的向量
H = relu(torch.matmul(X, W1) + b1)
return torch.matmul(H, W2) + b2
loss = torch.nn.CrossEntropyLoss() # 损失函数
训练模型:
num_epochs, lr = 5, 100.0
def evaluate_accuracy(data_iter, net):
acc_sum, n = 0.0, 0
for X, y in data_iter:
acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
n += y.shape[0]
return acc_sum / n
def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size,
params=None, lr=None, optimizer=None):
for epoch in range(num_epochs):
train_l_sum, train_acc_sum, n = 0.0, 0.0, 0
for X, y in train_iter:
y_hat = net(X)
l = loss(y_hat, y).sum()
# 梯度清零
if optimizer is not None:
optimizer.zero_grad() # 这里我们用到优化器,所以直接对优化器行梯度清零
elif params is not None and params[0].grad is not None:
for param in params:
param.grad.data.zero_()
l.backward()
if optimizer is None:
sgd(params, lr, batch_size)
else:
optimizer.step() # 用到优化器这里
train_l_sum += l.item()
train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item()
n += y.shape[0]
test_acc = evaluate_accuracy(test_iter, net)
print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f'
% (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc))
train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params, lr)