pytorch 5 classification 分類

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

n_data = torch.ones(100, 2)  # 100個具有2個屬性的數據 shape=(100,2)
x0 = torch.normal(2*n_data, 1)  # 根據原始數據生成隨機數據，第一個參數是均值，第二個是方差，這里設置為1了，shape=(100,2)
y0 = torch.zeros(100)  # 100個0作為第一類數據的標簽，shape=(100,1)
x1 = torch.normal(-2*n_data, 1)
y1 = torch.ones(100)

x = torch.cat((x0, x1), 0).type(torch.FloatTensor)  # cat數據合並 32-bit floating
y = torch.cat((y0, y1), 0).type(torch.LongTensor)   # 64-bit integer

x, y = Variable(x), Variable(y)

plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], s=100, lw=0)
plt.show()


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.predict = torch.nn.Linear(n_hidden, n_output)

    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x

net = Net(2, 10, 2)  # 數據是二維的所以輸入特征是2，輸出是兩種類別所以輸出層特征是2
print(net)

> Net(
>   (hidden): Linear(in_features=2, out_features=10, bias=True)
>   (predict): Linear(in_features=10, out_features=2, bias=True)
> )

# plt.ion()
plt.show()

optimizer = torch.optim.SGD(net.parameters(), lr=0.02)
loss_func = torch.nn.CrossEntropyLoss()  # 交叉熵 CrossEntropy [0.1, 0.2, 0.7] [0,0,1] 數據越大，是這一類的概率越大

for t in range(100):
    out = net.forward(x)     # 數據經過所有的網絡，輸出預測值

    loss = loss_func(out, y) # 輸入與預測值之間的誤差loss

    optimizer.zero_grad()    # 梯度重置
    loss.backward()          # 損失值反向傳播，計算梯度
    optimizer.step()         # 梯度優化    

    if t % 2 == 0:
        # 畫圖部分 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(0.5)

# plt.ioff()
plt.show()

END