參考

3.7. softmax回歸的簡潔實現

使用pytorch實現softmax

import torch
from torch import nn
from torch.nn import init
import numpy as np
import sys
sys.path.append("..")
import d2lzh_pytorch as d2l

3.7.1. 獲取和讀取數據

batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)

3.7.2. 定義和初始化模型

num_inputs = 784
num_outputs = 10class LinearNet(nn.Module):def __init__(self, num_inputs, num_outputs):super(LinearNet, self).__init__()self.linear = nn.Linear(num_inputs, num_outputs)  def forward(self, x):y = self.linear(x.view(x.shape[0], -1))return y
net = LinearNet(num_inputs, num_outputs)init.normal_(net.linear.weight, mean=0, std=0.01)
init.constant_(net.linear.bias, val=0)

3.7.3. softmax和交叉熵損失函數

loss = nn.CrossEntropyLoss()

3.7.4. 定義優化算法

optimizer = torch.optim.SGD(net.parameters(), lr=0.1)

3.7.5. 訓練模型

num_epochs = 5
d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

3.7.6. 測試

# 測試
X, y = iter(test_iter).next()true_labels = d2l.get_fashion_mnist_labels(y.numpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(dim=1).numpy())
titles = [true + '\n' + pred for true, pred in zip(true_labels, pred_labels)]d2l.show_fashion_mnist(X[0:9], titles[0:9])