PyTorch(七) --处理多维特征的输入

第7讲 处理多维特征的输入

传送门 处理多维特征的输入

课程代码：

# -*- coding: UTF-8 -*-
'''===============================================
@Author ：kidding
@Date   ：2021/2/7 16:15
@File   ：Processing_Multi-Dimensional_Feature_Input
@IDE    ：PyCharm
=================================================='''
import torch
import numpy as np
import matplotlib.pyplot as plt

'''
1、Prepare DataSet
'''
xy = np.loadtxt('./dataset/diabetes.csv.gz', delimiter=',', dtype=np.float32)#加载训练集
x_data = torch.from_numpy(xy[:, :-1]) # 取前八列   第一个‘：’是指读取所有行，第二个‘：’是指从第一列开始，最后一列不要
y_data = torch.from_numpy(xy[:, [-1]]) # 取最后一列    [-1] 最后得到的是个矩阵
'''
2、Design model
'''
class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
        self.linear1 = torch.nn.Linear(8,6)
        self.linear2 = torch.nn.Linear(6,4)
        self.linear3 = torch.nn.Linear(4,1)
        self.sigmoid = torch.nn.Sigmoid()

    def forward(self,x):
        x = self.sigmoid(self.linear1(x))
        x = self.sigmoid(self.linear2(x))#将上面一行的输出作为输入
        x = self.sigmoid(self.linear3(x))#将上面一行的输出作为输入
        return x

model = Model()

'''
3、construct loss and optimizer
'''
criterion = torch.nn.BCELoss(size_average=True)
#model.parameters()会扫描module中的所有成员，如果成员中有相应权重，那么都会将结果加到要训练的参数集合上
optimizer = torch.optim.SGD(model.parameters(), lr = 0.1)#lr为学习率，因为0.01太小了，我改成了0.1

Epoch_list =[]  #保存epoch
Loss_list = []  #保存每个epoch对应的loss

'''
4、Training Cycle : forward-->backward-->update
'''
for epoch in range(1000):
    # Forward
    y_pred = model(x_data)
    loss = criterion(y_pred,y_data)
    print("Epoch:", epoch,  "loss ={:.5f}".format(loss.item()))

    Epoch_list.append(epoch)
    Loss_list.append(loss)

    # Backward
    optimizer.zero_grad()   # 梯度置为0
    loss.backward() # 反向传播

    # update
    optimizer.step()    # 更新w和b的值

'''
5、Painting
'''
plt.plot(Epoch_list,Loss_list)
plt.title("SGD")
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.grid(ls='--')  # 生成网格
plt.show()

# 参数说明
# 第一层的参数：
layer1_weight = model.linear1.weight.data
layer1_bias = model.linear1.bias.data
print("layer1_weight", layer1_weight)
print("layer1_weight.shape", layer1_weight.shape)
print("layer1_bias", layer1_bias)
print("layer1_bias.shape", layer1_bias.shape)
# 第一层的参数：
layer2_weight = model.linear2.weight.data
layer2_bias = model.linear2.bias.data
print("layer2_weight", layer2_weight)
print("layer2_weight.shape", layer2_weight.shape)
print("layer2_bias", layer2_bias)
print("layer2_bias.shape", layer2_bias.shape)
# 第一层的参数：
layer3_weight = model.linear3.weight.data
layer3_bias = model.linear3.bias.data
print("layer3_weight", layer3_weight)
print("layer3_weight.shape", layer3_weight.shape)
print("layer3_bias", layer3_bias)
print("layer3_bias.shape", layer3_bias.shape)

网络参数如下：

最终实现的网络效果：

Loss损失图：

思考：为什么训练的Loss只能到0.6？如何让进一步降低训练的Loss值？