[人工智能]PyTorh深度学习实践——多维度特征输入

import torch
import matplotlib.pyplot as plt
import numpy as np

xy = np.loadtxt('diabetes.csv',delimiter=',',dtype=np.float32)
x_data = torch.from_numpy(xy[:,:-1])
#print(x_data)
y_data =torch.from_numpy(xy[:,[-1]])
#print(y_data)
epoch_list = []
loss_list = []



class Model(torch.nn.Module):
    def __init__(self):
        super(Model,self).__init__()
       # self,linear = torch.nn.Linear(8,1)#输入8维特征维，输出1维特征维

        self.linear1 = torch.nn.Linear(8,6)
        self.linear2 = torch.nn.Linear(6,4)
        self.linear3 = torch.nn.Linear(4,1)
        self.sigmod = torch.nn.Sigmoid()
        self.activate = torch.nn.ReLU()

    def forward(self,x):
        x = self.activate(self.linear1(x))
        x = self.activate(self.linear2(x))
        x = self.sigmod(self.linear3(x))
        return x


model = Model()

criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(),lr=0.05)

for epoch in range(10000):
    y_pred = model(x_data)
    loss = criterion(y_pred,y_data)
    print(f'epoch = {epoch}  loss = {loss.data:.2f}')

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    epoch_list.append(epoch)
    loss_list.append(loss.item())
x_test = torch.tensor([[-0.294118,0.487437,0.180328,-0.292929,0,0.00149028,-0.53117,-0.0333333]])
print(x_test)
y_test =model(x_test)
print(y_test.item())
x_test2 =torch.tensor([[-0.176471,0.959799,0.147541,-0.333333,-0.65721,-0.251863,-0.927412,0.133333]])
print(model(x_test2).item())
plt.plot(epoch_list,loss_list)
plt.xlabel('Epoch')
plt.ylabel('loss')
plt.show()

import torch
import numpy as np
from torch.utils.data import Dataset,DataLoader
import matplotlib.pyplot as plt

class Datasets(Dataset):
    def __init__(self,filepath):
        xy = np.loadtxt(filepath,delimiter=',',dtype=np.float32)
        self.len = xy.shape[0]
        self.x_data = torch.from_numpy(xy[:,:-1])
        self.y_data = torch.from_numpy(xy[:,[-1]])

    def __getitem__(self, index):
        return self.x_data[index],self.y_data[index]

    def __len__(self):
        return self.len

dataset = Datasets('diabetes.csv')
train_loader = DataLoader(dataset=dataset,batch_size=32,shuffle=True ,num_workers=3)

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.sigmod = torch.nn.Sigmoid()
        self.relu  =  torch.nn.ReLU()

    def forward(self,x):
        x = self.sigmod(self.linear1(x))
        x = self.sigmod(self.linear2(x))
        x = self.sigmod(self.linear3(x))
        return x

model = Model()

criterion = torch.nn.BCELoss(reduction='mean')
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)

epoch_list =[]
loss_list = []
num=0
if __name__ =='__main__':
    for epoch in range(100):
        for i ,data in enumerate(train_loader,0):
            #print(data)
            inputs,labels = data
            y_pred = model(inputs)
            loss = criterion(y_pred,labels)
            print(epoch,i,loss.item())
            loss_list.append(loss.item())
            #print(loss_list)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            epoch_list.append(num)
            num = num + 1
    plt.plot(epoch_list,loss_list)
    plt.xlabel('epoch')
    plt.ylabel('loss')
    plt.show()