作业：pytorch实现图卷机网络，与随机梯度下降法实现

最新推荐文章于 2024-09-10 17:15:34 发布

Dream_Henry

最新推荐文章于 2024-09-10 17:15:34 发布

阅读量1k

点赞数

文章标签： pytorch 网络深度学习

本文链接：https://blog.csdn.net/qq_42994498/article/details/121296606

版权

该博客介绍了图卷积网络（GCN）在节点分类任务中的应用，使用了PyTorch Geometric库实现。模型经过200个训练轮次后，在Cora数据集上评估准确性。同时，文章还展示了随机梯度下降法求解线性方程组的实例，通过迭代更新参数，最终得出解决方案。

摘要由CSDN通过智能技术生成

核心代码：
图卷积网络

import torch
import torch.nn.functional as F
from torch_geometric.nn import GCNConv

from torch_geometric.datasets import Planetoid
dataset = Planetoid(root='/tmp/Cora', name='Cora')

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = GCNConv(dataset.num_node_features, 16)
        self.conv2 = GCNConv(16, dataset.num_classes)

    def forward(self, data):
        x, edge_index = data.x, data.edge_index
        x = self.conv1(x, edge_index)
        x = F.relu(x)
        x = F.dropout(x, training=self.training)
        x = self.conv2(x, edge_index)
        return F.log_softmax(x, dim=1)

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = Net().to(device)
data = dataset[0].to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.01, weight_decay=5e-4)

model.train()
for epoch in range(200):
    optimizer.zero_grad()
    out = model(data)
    loss = F.nll_loss(out[data.train_mask], data.y[data.train_mask])
    loss.backward()
    optimizer.step()

model.eval()
_, pred = model(data).max(dim=1)
correct = float(pred[data.test_mask].eq(data.y[data.test_mask]).sum().item())
acc = correct / data.test_mask.sum().item()
print('Accuracy: {:.4f}'.format(acc))

随机梯度下降法


import numpy as np
import math
import random

x = np.random.choice(np.array([2104, 1600, 2400, 1416, 3000]),5)
x1 = np.random.choice(np.array([3,3,3,2,4]),5)
t = np.random.choice(np.array([400, 330, 369, 232, 540]),5)
a = 0.0000100

error = 0.00001

dert = random.random() 
dert1 = random.random()
dert2 = random.random()

sit = random.random()
sit2 = random.random()
sit3 = random.random()

for i in range(0, 5):
     while (dert > error or dert1 > error or dert2 > error):
        dert = (sit+sit2*x[i]+sit3*x1[i]-t[i])*1

        dert1 = (sit + sit2 * x[i] + sit3 * x1[i] - t[i]) * x[i]

        dert2 = (sit + sit2 * x[i] + sit3 * x1[i] - t[i]) * x1[i]

        sit = sit - dert * a
        sit2 = sit2 - dert1*a
        sit3 = sit3 - dert2*a

print(dert)
print(dert1)
print(dert2)

print(sit)
print(sit2)
print(sit3)

x3 = 3600
x4 = 5
h = sit + sit2*x3 + sit3*x4
print(h)