鸢尾花分类（利用pytorch实现）

导入库

import numpy as np
import torch
from collections import Counter
from sklearn import datasets
import torch.nn.functional as Fun

1. 数据准备

dataset = datasets.load_iris()
dataut=dataset['data']
priciple=dataset['target']
input=torch.FloatTensor(dataset['data'])
label=torch.LongTensor(dataset['target'])

2. 定义BP神经网络

class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_feature, n_hidden) 
        self.out = torch.nn.Linear(n_hidden, n_output)   
    def forward(self, x):
        x = Fun.relu(self.hidden(x))      
        x = self.out(x)                   
        return x

3. 定义优化器损失函数

net = Net(n_feature=4, n_hidden=20, n_output=3)   
optimizer = torch.optim.SGD(net.parameters(), lr=0.02) # 优化器选用随机梯度下降方式
loss_func = torch.nn.CrossEntropyLoss() # 对于多分类一般采用的交叉熵损失函数,

4. 训练数据

for t in range(500):
    out = net(input)              
    loss = loss_func(out, label)     
    optimizer.zero_grad()   # 梯度清零
    loss.backward()         # 前馈操作
    optimizer.step()        # 使用梯度优化器

5. 得出结果

out = net(input) 
prediction = torch.max(out, 1)[1] 
pred_y = prediction.data.numpy()
target_y = label.data.numpy()

6.衡量准确率

accuracy = float((pred_y == target_y).astype(int).sum()) / float(target_y.size)
print("莺尾花预测准确率",accuracy)