完整糖尿病pytorch框架

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

class LinearExample(torch.nn.Module):
    def __init__(self):
        super(LinearExample, self).__init__()
        self.linear1 = torch.nn.Linear(8,6)
        self.linear2 = torch.nn.Linear(6,4)
        self.linear3 = torch.nn.Linear(4,1)
        # self.linear4 = torch.nn.Linear(2,1)
        self.sigmoid = torch.nn.Sigmoid()
        self.relu = torch.nn.ReLU()

    def forward(self,x):
        x = self.relu(self.linear1(x))
        x = self.relu(self.linear2(x))
        x = self.linear3(x)
        # x = self.linear4(x)
        return self.relu(x)
        # return self.sigmoid(x)

class DiabetesDatset(Dataset):
    def __init__(self):
        data_xy = np.loadtxt('/home/chasing/Documents/pytorchbooklit/diabetes.csv.gz', delimiter=',', dtype=np.float32)
        self.len = data_xy.shape[0]
        self.data_x = torch.from_numpy(data_xy[:,:-1])
        self.data_y = torch.from_numpy(data_xy[:,-1]).reshape(-1,1)

    def __getitem__(self, index):
        return self.data_x[index], self.data_y[index]

    def __len__(self):
        return self.len

model = LinearExample()
dataset = DiabetesDatset()
train_loader =  DataLoader(dataset=dataset, batch_size=32, shuffle=True, num_workers=2)
criterion = torch.nn.BCELoss(size_average=True)
optimizer = torch.optim.SGD(model.parameters(), lr=1e-2)

loss_list = list()

if __name__ == '__main__':
    for epoch in range(100):
        for i, data in enumerate(train_loader, 0):
            inputs, labels = data

            y_pred = model(inputs)
            loss = criterion(y_pred, labels)

            optimizer.zero_grad()
            loss.backward()

            optimizer.step()
            loss_list.append(loss)

    plt.plot(loss_list)
    plt.show()