【PyTorch深度学习六】逻辑斯蒂回归

代码1

import torchvision
train_set = torchvision.datasets.MNIST(root='../dataset/mnist', train=True, download=True)
test_set = torchvision.datasets.MNIST(root='../dataset/mnist', train=False, download=True)

结果：

Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz
Downloading http://192.168.112.2/cache/4/02/yann.lecun.com/34152be34c1115808d82493371362afe/train-images-idx3-ubyte.gz to ../dataset/mnist\MNIST\raw\train-images-idx3-ubyte.gz
100.0%
Extracting ../dataset/mnist\MNIST\raw\train-images-idx3-ubyte.gz to ../dataset/mnist\MNIST\raw

Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz
Downloading http://192.168.112.2/cache/7/02/yann.lecun.com/32a667c2f3de678798ae039d04726fa1/train-labels-idx1-ubyte.gz to ../dataset/mnist\MNIST\raw\train-labels-idx1-ubyte.gz
100.0%
Extracting ../dataset/mnist\MNIST\raw\train-labels-idx1-ubyte.gz to ../dataset/mnist\MNIST\raw

Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz
Downloading http://192.168.112.2/cache/12/02/yann.lecun.com/b80c4efc17eabb28908f865775412435/t10k-images-idx3-ubyte.gz to ../dataset/mnist\MNIST\raw\t10k-images-idx3-ubyte.gz
100.0%
Extracting ../dataset/mnist\MNIST\raw\t10k-images-idx3-ubyte.gz to ../dataset/mnist\MNIST\raw

Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz
Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to ../dataset/mnist\MNIST\raw\t10k-labels-idx1-ubyte.gz
100.0%
Extracting ../dataset/mnist\MNIST\raw\t10k-labels-idx1-ubyte.gz to ../dataset/mnist\MNIST\raw


Process finished with exit code 0

代码2

# import torch.nn
# import torchvision
# train_set = torchvision.datasets.MNIST(root='../dataset/mnist', train=True, download=True)
# test_set = torchvision.datasets.MNIST(root='../dataset/mnist', train=False, download=True)
import torch
# import torch.nn.functional as F
import numpy as np
import matplotlib.pyplot as plt

x_data = torch.Tensor([[1.0], [2.0], [3.0]])
y_data = torch.Tensor([[0], [0], [1]])

class LogistRegressionModel(torch.nn.Module):
    def __init__(self):
        super(LogistRegressionModel, self).__init__()
        self.linear = torch.nn.Linear(1, 1)

    def forward(self, x):
        y_pred = torch.sigmoid(self.linear(x))
        return y_pred

model = LogistRegressionModel()

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

for epoch in range(1000):
    y_pred = model(x_data)
    Loss = criterion(y_pred, y_data)
    print(epoch, Loss)
    optimizer.zero_grad()
    Loss.backward()
    optimizer.step()

x = np.linspace(1, 10, 200)
x_t = torch.Tensor(x).view((200,1))
y_t = model(x_t)
y = y_t.data.numpy()
plt.plot(x, y)
plt.plot([0, 10], [0.5, 0.5], c = 'r')
plt.xlabel('Hours')
plt.ylabel('Probability of Pass')
plt.grid()
plt.show()

部分结果：

0 tensor(2.4286, grad_fn=<BinaryCrossEntropyBackward0>)
1 tensor(2.4056, grad_fn=<BinaryCrossEntropyBackward0>)
2 tensor(2.3841, grad_fn=<BinaryCrossEntropyBackward0>)
3 tensor(2.3639, grad_fn=<BinaryCrossEntropyBackward0>)
4 tensor(2.3451, grad_fn=<BinaryCrossEntropyBackward0>)
5 tensor(2.3274, grad_fn=<BinaryCrossEntropyBackward0>)
6 tensor(2.3108, grad_fn=<BinaryCrossEntropyBackward0>)
7 tensor(2.2954, grad_fn=<BinaryCrossEntropyBackward0>)
8 tensor(2.2809, grad_fn=<BinaryCrossEntropyBackward0>)
9 tensor(2.2673, grad_fn=<BinaryCrossEntropyBackward0>)
10 tensor(2.2546, grad_fn=<BinaryCrossEntropyBackward0>)
11 tensor(2.2428, grad_fn=<BinaryCrossEntropyBackward0>)
12 tensor(2.2316, grad_fn=<BinaryCrossEntropyBackward0>)
13 tensor(2.2212, grad_fn=<BinaryCrossEntropyBackward0>)
14 tensor(2.2114, grad_fn=<BinaryCrossEntropyBackward0>)
15 tensor(2.2022, grad_fn=<BinaryCrossEntropyBackward0>)
...
984 tensor(1.0718, grad_fn=<BinaryCrossEntropyBackward0>)
985 tensor(1.0713, grad_fn=<BinaryCrossEntropyBackward0>)
986 tensor(1.0708, grad_fn=<BinaryCrossEntropyBackward0>)
987 tensor(1.0703, grad_fn=<BinaryCrossEntropyBackward0>)
988 tensor(1.0698, grad_fn=<BinaryCrossEntropyBackward0>)
989 tensor(1.0693, grad_fn=<BinaryCrossEntropyBackward0>)
990 tensor(1.0688, grad_fn=<BinaryCrossEntropyBackward0>)
991 tensor(1.0683, grad_fn=<BinaryCrossEntropyBackward0>)
992 tensor(1.0678, grad_fn=<BinaryCrossEntropyBackward0>)
993 tensor(1.0673, grad_fn=<BinaryCrossEntropyBackward0>)
994 tensor(1.0668, grad_fn=<BinaryCrossEntropyBackward0>)
995 tensor(1.0663, grad_fn=<BinaryCrossEntropyBackward0>)
996 tensor(1.0658, grad_fn=<BinaryCrossEntropyBackward0>)
997 tensor(1.0653, grad_fn=<BinaryCrossEntropyBackward0>)
998 tensor(1.0648, grad_fn=<BinaryCrossEntropyBackward0>)
999 tensor(1.0643, grad_fn=<BinaryCrossEntropyBackward0>)