參考

3.10. 多重感知機的簡潔實現(xiàn)

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

3.10.1. 定義模型

num_inputs, num_outputs, num_hiddens = 784, 10, 256 # 參數(shù)都存在 net.parameters()中 net = nn.Sequential(d2l.FlattenLayer(),nn.Linear(num_inputs, num_hiddens),nn.ReLU(),nn.Linear(num_hiddens, num_outputs), )# 初始化權(quán)重值 for param in net.parameters():init.normal_(param, mean=0, std=0.01)

3.10.2 讀取數(shù)據(jù)并訓練模型

batch_size = 256 train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size) loss = torch.nn.CrossEntropyLoss()optimizer = torch.optim.SGD(net.parameters(), lr = 0.5)num_epochs = 5 d2l.train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, None, None, optimizer)

### 3.10.3 預測# 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])

總結(jié)

以上是生活随笔為你收集整理的[pytorch、学习] - 3.10 多重感知机的简洁实现的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。