python
复制代码
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)
3.7.1 初始化模型参数
python
复制代码
net = nn.Sequential(nn.Flatten(), nn.Linear(784, 10))
def init_weights(m):
if type(m) == nn.Linear:
nn.init.normal_(m.weight, std=0.01)
net.apply(init_weights);
3.7.2 重新审视Softmax的实现
python
复制代码
loss = nn.CrossEntropyLoss(reduction='none')
3.7.3 优化算法
python
复制代码
# 在这里，我们(使用学习率为0.1的小批量随机梯度下降作为优化算法)
trainer = torch.optim.SGD(net.parameters(), lr=0.1)
3.7.4 训练
python
复制代码
num_epochs = 10
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, trainer)
3.7.5 预测
python
复制代码
batch_size = 256 #迭代器批量
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
def predict_ch3(net, test_iter, n=6):
"""Predict labels (defined in Chapter 3)."""
for X, y in test_iter: # 获取第一批测试数据
break
trues = d2l.get_fashion_mnist_labels(y) # 真实标签转文本
preds = d2l.get_fashion_mnist_labels(d2l.argmax(net(X), axis=1)) # 预测标签转文本
titles = [true +'\n' + pred for true, pred in zip(trues, preds)] # 组合标签
d2l.show_images(d2l.reshape(X[0:n], (n, 28, 28)), 1, n, titles=titles[0:n]) # 可视化
predict_ch3(net, test_iter)
