2021-10-18

pytorch学习

import os
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt

torch.manual_seed(1)

#参数设置
EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

```python
#下载数据
if not(os.path.exists('F:\\python project\\pytorch\\mnist\\')):
    #not mnist dir or mnist is empty dir
    DOWNLOAD_MNIST = True
    print(DOWNLOAD_MNIST)

train_data = torchvision.datasets.MNIST(
    root='F:\\python project\\pytorch\\mnist\\',
    train=True,
    transform=torchvision.transforms.ToTensor(),  #converts a PIL.Image or numpy.ndarray to torch.FloatTensor of
                                                  #shape(C x H x W) and normalize in the range(0.0,1)
    download = DOWNLOAD_MNIST
)

print(train_data.train_data.size())
print(train_data.train_labels.size())
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
#plt.show()

在这里插入代码片

train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

test_data = torchvision.datasets.MNIST( root='F:\\python project\\pytorch\\mnist\\', train=False)
#shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.
#type():当不指定dtype时,返回类型.
	   #当指定dtype时,返回类型转换后的数据,如果类型已经符合要求,
	   #那么不做额外的复制,返回原对象.
test_y = test_data.test_labels[:2000]

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(  #输入结果（1，28，28）
            nn.Conv2d(
                in_channels=1,  # input height
                out_channels=16,  # 16个筛选器，每个筛选器得出一个特征
                kernel_size=5,  # 筛选器大小
                stride=1,  #筛选器每次移动一步
                padding=2  # 在边缘添加2圈白色像素点使得和输入图片大小一致
                           #padding=(kernel_size-1)/2
            ),     #输出结果（16，28，28）
           nn.ReLU(),
           nn.MaxPool2d(kernel_size=2)   #在2x2的区域中选出最大值，输出结果（16，14，14）

        )
        self.conv2 = nn.Sequential(       #输入结果（16，28，28）
            nn.Conv2d(16, 32, 5, 1, 2),  #输出结果（32，14，14）
            nn.ReLU(),
            nn.MaxPool2d(2)      #输出结果（32，7，7）
        )
        self.out = nn.Linear(32*7*7,10)     #全连接神经元，输出10个集合

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output, x

cnn = CNN()
print(cnn)

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):
        b_x = Variable(x)
        b_y = Variable(y)

        output = cnn(b_x)[0]
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 100 == 0:
            test_output, last_layer = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.squeeze()
            accuracy = (pred_y == test_y).sum().item() / float(test_y.size(0))
            print('Epoch:', epoch, '| train loss:%.4f' % loss.item(), '|test accuracy:%.2f' % accuracy)

test_output, _ = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
print(pred_y, 'prediction number')
print(test_y[:10].numpy(), 'real number')