单隐藏层的多层感知机从零实现
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)
还是之前的数据集fashion_mnist
初始化模型参数
num_inputs, num_outputs, num_hiddens = 784, 10, 256
W1 = nn.Parameter(torch.randn(num_inputs, num_hiddens, 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]
单隐藏层
W1:784 * 256
b1: 256 * 1
W2: 256 * 10
b2:10 * 1
激活函数Relu
def relu(X):
a = torch.zeros_like(X)
return torch.max(X, a)
模型
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)
W2,b2是输出层的参数,没有激活函数
X:样本数 * 784
损失函数
loss = nn.CrossEntropyLoss(reduction='none')
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)
单隐藏层的多层感知机简易实现
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);
batch_size, lr, num_epochs = 256, 0.1, 10
loss = nn.CrossEntropyLoss(reduction='none')
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)
经过了线性回归和softmax回归,上面很容易就能看懂了。