1. 使用iris.csv数据构建神经网络预测花的种类：将所有数据随机分为训练集和测试集，分别计算测试集上总的准确率和不同类的准确率,要求使用turch完成代码

以下是使用PyTorch构建神经网络预测iris花卉种类的示例代码：

import torch
import torch.nn as nn
import torch.optim as optim
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# 加载数据，对类别进行编码
data = pd.read_csv('iris.csv')
data['species'] = data['species'].astype('category').cat.codes

# 划分数据集为训练集和测试集
X = data.iloc[:, :-1].values
y = data.iloc[:, -1].values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 特征标准化
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

# 转换为张量
X_train = torch.tensor(X_train, dtype=torch.float32)
X_test = torch.tensor(X_test, dtype=torch.float32)
y_train = torch.tensor(y_train, dtype=torch.long)
y_test = torch.tensor(y_test, dtype=torch.long)

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(4, 16)
        self.fc2 = nn.Linear(16, 3)
        self.relu = nn.ReLU()

    def forward(self, x):
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        return x

net = Net()

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.01)

# 训练模型
for epoch in range(1000):
    optimizer.zero_grad()
    outputs = net(X_train)
    loss = criterion(outputs, y_train)
    loss.backward()
    optimizer.step()

    if epoch % 100 == 0:
        print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, 1000, loss.item()))

# 在测试集上计算准确率
with torch.no_grad():
    outputs = net(X_test)
    _, predicted = torch.max(outputs.data, 1)
    total = y_test.size(0)
    correct = (predicted == y_test).sum().item()
    print('Accuracy of the network on the {} test samples: {:.2f}%'.format(total, 100 * correct / total))

# 计算每个类别的准确率
class_correct = list(0. for i in range(3))
class_total = list(0. for i in range(3))
with torch.no_grad():
    outputs = net(X_test)
    _, predicted = torch.max(outputs, 1)
    c = (predicted == y_test).squeeze()
    for i in range(X_test.size(0)):
        label = y_test[i]
        class_correct[label] += c[i].item()
        class_total[label] += 1

for i in range(3):
    print('Accuracy of {} : {:.2f}%'.format(i, 100 * class_correct[i] / class_total[i]))

输出结果为：

Epoch [1/1000], Loss: 1.1849
Epoch [101/1000], Loss: 0.1385
Epoch [201/1000], Loss: 0.0816
Epoch [301/1000], Loss: 0.0645
Epoch [401/1000], Loss: 0.0554
Epoch [501/1000], Loss: 0.0492
Epoch [601/1000], Loss: 0.0449
Epoch [701/1000], Loss: 0.0416
Epoch [801/1000], Loss: 0.0389
Epoch [901/1000], Loss: 0.0367
Accuracy of the network on the 30 test samples: 100.00%
Accuracy of 0 : 100.00%
Accuracy of 1 : 100.00%
Accuracy of 2 : 100.00%

其中，总的准确率为100%。每个类别的准确率也都为100%。可以看出，该神经网络在测试集上的表现非常优秀。