Python：（人工智能识别手写数字）使用卷积神经网络代码多个报错及相应解决方法

Posted 2022-12-02 方舟aark

整个卷积神经网络代码（入门：识别手写数字）如下：

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

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(
    root='./mnist',
    train=True,
    transform=torchvision.transforms.ToTensor(),
    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()

train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=2)

test_data = torchvision.datasets.MNIST(root='./mnist',train=False)
test_x = Variable(torch.unsqueeze(test_data.test_data,dim=1),volatile=True).type(torch.FloatTensor)[:2000]/255.
test_y = test_data.test_labels[:2000]

class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,
                out_channels=16,
                kernel_size=5,
                stride=1,
                padding=2, # (5-1)/2
            ),
            nn.ReLU,
            nn.MaxPool2d(kernel_size=2),
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16,32,5,1,2),
            nn.ReLU,
            nn.MaxPool2d(2)
        )
        self.out = nn.Linear(32*7*7,10)

    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
cnn = CNN()
# for(b_x,b_y) in train_loader:
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)
        loss = loss_func(output,b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)
            pred_y = torch.max(test_output,1)[1].data.squeeze()
            accuracy = sum(pred_y == test_y) / test_y.size(0)
            print('Epoch:',epoch,'| train loss: %.4f' % loss.data[0],'| 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')

第一次使用的时候记得将DOWNLOAD_MNIST改成True。

第一个报错：

TypeError: torch.nn.modules.activation.ReLU is not a Module subclass

解决方法：应当将代码中nn.ReLU改为nn.ReLU()。

第二个报错：

RuntimeError: DataLoader worker (pid(s) 8772, 8773) exited unexpectedly

解决方法：将 train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=2) 中的num_workers=2改为0。

第三个报错：

IndexError: invalid index of a 0-dim tensor. Use tensor.item() in Python or tensor.item<T>() in C++ to convert a 0-dim tensor to a number

解决方法：将 print(‘Epoch:’,epoch,‘| train loss: %.4f’ % loss.data[0],‘| test accuracy: %.2f’ % accuracy) 中的loss.data[0]改为：loss.item() 。

修改后的代码：

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

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(
    root='./mnist',
    train=True,
    transform=torchvision.transforms.ToTensor(),
    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()

train_loader = Data.DataLoader(dataset=train_data,batch_size=BATCH_SIZE,shuffle=True,num_workers=0)

test_data = torchvision.datasets.MNIST(root='./mnist',train=False)
test_x = Variable(torch.unsqueeze(test_data.test_data,dim=1),volatile=True).type(torch.FloatTensor)[:2000]/255.
test_y = test_data.test_labels[:2000]

class CNN(nn.Module):
    def __init__(self):
        super(CNN,self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,
                out_channels=16,
                kernel_size=5,
                stride=1,
                padding=2, # (5-1)/2
            ),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        self.conv2 = nn.Sequential(
            nn.Conv2d(16,32,5,1,2),
            nn.ReLU(),
            nn.MaxPool2d(2)
        )
        self.out = nn.Linear(32*7*7,10)

    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
cnn = CNN()
# for(b_x,b_y) in train_loader:
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)
        loss = loss_func(output,b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)
            pred_y = torch.max(test_output,1)[1].data.squeeze()
            accuracy = sum(pred_y == test_y) / 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')