莫煩PyTorch學習筆記(三)——分類

---

本文主要是用PyTorch來實現一個簡單的分類任務。
編輯器：spyder

1.引入相應的包及建立數據集

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

# 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

# torch can only train on Variable, so convert them to Variable
x, y = Variable(x), Variable(y)

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

torch.normal()在這裏返回的是大小爲100x2的Tensor，每個元素的標準差爲1(通過normal的第二個參數設置獲得)。torch.cat()拼接Tensor，第二個參數表示拼接的維度。0表示爲按縱向拼接，這裏拼接後的大小爲400x2，1表示橫向拼接，該參數默認爲0。

輸入模型的數據應該是浮點型，類別標籤爲整型。這裏通過type()進行設置。

2.建立神經網絡

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

這裏的網絡跟前一篇迴歸中的是一樣的，只不過輸入輸出的維度發生了點變化。

Net (
  (hidden): Linear (2 -> 10)
  (out): Linear (10 -> 2)
)

3.訓練網絡

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

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

在這裏我們是進行分類任務，所以我們採用交叉熵torch.nn.CrossEntropyLoss()作爲損失函數。損失函數中包含了LogSoftMax的計算，所以直接將網絡全連接層的輸出輸進損失函數即可。其內部運行原理見下式：

loss(x, class) = -log(exp(x[class]) / (\sum_j exp(x[j])))
               = -x[class] + log(\sum_j exp(x[j]))

4.可視化訓練過程

plt.ion()   # something about plotting

for t in range(100):
    ...

    if t % 2 == 0:
        # plot and show learning process
        plt.cla()
        prediction = torch.max(F.softmax(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 = sum(pred_y == target_y)/200.
        plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color':  'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()

torch.max()返回的是兩個Variable，第一個Variable存的是最大值，第二個存的是其對應的位置索引index。這裏我們想要得到的是索引，所以後面用[1]。

5.運行結果