pytorch自動求導與邏輯迴歸

自動求導

retain_graph設爲True,可以進行兩次反向傳播

邏輯迴歸

import torch
import torch.nn as nn
import matplotlib.pyplot as plt
import numpy as np
torch.manual_seed(10)
#========生成數據=============
sample_nums = 100
mean_value = 1.7
bias = 1
n_data = torch.ones(sample_nums,2)
x0 = torch.normal(mean_value*n_data,1)+bias#類別0數據
y0 = torch.zeros(sample_nums)#類別0標籤
x1 = torch.normal(-mean_value*n_data,1)+bias#類別1數據
y1 = torch.ones(sample_nums)#類別1標籤
train_x = torch.cat((x0,x1),0)
train_y = torch.cat((y0,y1),0)
#==========選擇模型===========
class LR(nn.Module):
    def __init__(self):
        super(LR,self).__init__()
        self.features = nn.Linear(2,1)
        self.sigmoid = nn.Sigmoid()

    def forward(self,x):
        x = self.features(x)
        x = self.sigmoid(x)
        return x

lr_net = LR()#實例化邏輯迴歸模型

#==============選擇損失函數===============
loss_fn = nn.BCELoss()
#==============選擇優化器=================
lr = 0.01
optimizer = torch.optim.SGD(lr_net.parameters(),lr = lr,momentum=0.9)

#===============模型訓練==================
for iteration in range(1000):
    #前向傳播
    y_pred = lr_net(train_x)#模型的輸出
    #計算loss
    loss = loss_fn(y_pred.squeeze(),train_y)
    #反向傳播
    loss.backward()
    #更新參數
    optimizer.step()

    #繪圖
    if iteration % 20 == 0:
        mask = y_pred.ge(0.5).float().squeeze() #以0.5分類
        correct = (mask==train_y).sum()#正確預測樣本數
        acc = correct.item()/train_y.size(0)#分類準確率

        plt.scatter(x0.data.numpy()[:,0],x0.data.numpy()[:,1],c='r',label='class0')
        plt.scatter(x1.data.numpy()[:,0],x1.data.numpy()[:,1],c='b',label='class1')

        w0,w1 = lr_net.features.weight[0]
        w0,w1 = float(w0.item()),float(w1.item())
        plot_b = float(lr_net.features.bias[0].item())
        plot_x = np.arange(-6,6,0.1)
        plot_y = (-w0*plot_x-plot_b)/w1

        plt.xlim(-5,7)
        plt.ylim(-7,7)
        plt.plot(plot_x,plot_y)

        plt.text(-5,5,'Loss=%.4f'%loss.data.numpy(),fontdict={'size':20,'color':'red'})
        plt.title('Iteration:{}\nw0:{:.2f} w1:{:.2f} b{:.2f} accuracy:{:2%}'.format(iteration,w0,w1,plot_b,acc))
        plt.legend()
        plt.show()
        plt.pause(0.5)
        if acc > 0.99:
            break