Classification分类

分类是机器学习中常见的另一任务，也是其应用最广的方面。本文通过简单的DNN以实现数据分类任务

1. 数据准备

import torch
import torch.nn.functional as F
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

# make fake data
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

# The code below is deprecated in Pytorch 0.4. Now, autograd directly supports tensors
# x, y = Variable(x), Variable(y)

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

2. 神经网络构建

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)   # hidden layer
        self.out = torch.nn.Linear(n_hidden, n_output)   # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))      # activation function for hidden layer
        x = self.out(x)
        return x

net = Net(n_feature=2, n_hidden=10, n_output=2)     # define the network
print(net)  # net architecture

1. 在分类问题中，神经层的输出必须是分类的类别总数
2. 分类问题中常用的激活函数是 Relu 和 Sigmoid

3. 优化器和损失函数选择

optimizer = torch.optim.SGD(net.parameters(), lr=0.02)
loss_func = torch.nn.CrossEntropyLoss()  # the target label is NOT an one-hotted

常用优化器包括：Adam ， ASGD， RMSprop， SGD等

4. 优化

for t in range(100):
    out = net(x)                 # input x and predict based on x
    loss = loss_func(out, y)     # must be (1. nn output, 2. target), the target label is NOT one-hotted

    optimizer.zero_grad()   # clear gradients for next train
    loss.backward()         # backpropagation, compute gradients
    optimizer.step()        # apply gradients

5. 画图

plt.ion()   # something about plotting
    if t % 2 == 0:
        # plot and show learning process
        plt.cla()
        prediction = torch.max(out, 1)[1]
        pred_y = prediction.data.numpy()
        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()