PyTorch学习（5）—分类

本篇博客主要介绍采用PyTorch对数据进行分类。

首先是分类数据（生成的假数据）：

示例代码：

import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt

# 生成假数据
n_data = torch.ones(100, 2)
x0 = torch.normal(2*n_data, 1)      # class0 x data (tensor), shape=(100, 2)
y0 = torch.zeros(100)               # class0 y data (tensor), shape=(100, 1)
x1 = torch.normal(-2*n_data, 1)     # class1 x data (tensor), shape=(100, 2)
y1 = torch.ones(100)                # class1 y data (tensor), shape=(100, 1)
x = torch.cat((x0, x1), 0).type(torch.FloatTensor)  # shape (200, 2) FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)    # shape (200,) LongTensor = 64-bit integer

# 将Tensor转换为torch
x, y = Variable(x), Variable(y)

# 打印数据散点图
# plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=y.data.numpy(), s=100, lw=0, cmap='RdYlGn')
# plt.show()


class Net(torch.nn.Module):
    # 初始化
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_feature, n_hidden)
        self.predict = torch.nn.Linear(n_hidden, n_output)

    # 前向传递
    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x


net = Net(2, 10, 2)
# 输出定义的网络的结构
print(net)
plt.ion()
plt.show()

# 优化(给出神经网络的参数和学习速率)
optimizer = torch.optim.SGD(net.parameters(), lr=0.02)
# loss function，分类问题：交叉熵（CrossEntropyLoss） [0.1, 0.2, 0.7]=1表示分为每个类的概率
loss_func = torch.nn.CrossEntropyLoss()

for t in range(100):
    out = net(x)
    # 求误差
    loss = loss_func(out, y)

    # 优化
    # 每一步首先将梯度降为0
    optimizer.zero_grad()
    # 进行反向传递更新参数
    loss.backward()
    # 优化梯度
    optimizer.step()

    if t % 2 == 0:
        # plot and show learning process
        plt.cla()
        prediction = torch.max(out, 1)[1]
        pred_y = prediction.data.numpy().squeeze()
        target_y = y.data.numpy()
        plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=pred_y, s=100, lw=0, cmap='RdYlGn')
        accuracy = float((pred_y == target_y).astype(int).sum()) / float(target_y.size)
        plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color': 'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()

分类过程：