I tried to build a machine learning model using CIFAR 10 dataset, but I am encountering a bug that my model stops training past i = 78 (looped 78 times, see code for more).
import torch import torchvision.transforms as transforms from torchvision.datasets import CIFAR10 from torchvision.transforms import ToTensor from torch.utils.data.dataloader import DataLoader transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) classes = ('plane', 'car', 'bird', 'cat','deer', 'dog', 'frog', 'horse', 'ship', 'truck') train_dataset = CIFAR10(root = './data', train = True, download = True, transform = transform) train_loader = DataLoader(train_dataset, batch_size = 4, shuffle = True, num_workers = 2) test_dataset = CIFAR10(root = './data', train = False, download = True, transform = transform) test_loader = DataLoader(test_dataset, batch_size = 128, shuffle = False, num_workers = 2) import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1, 16 * 5 * 5) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x net = Net() optimiser = torch.optim.SGD(model.parameters(), lr = 0.001, momentum=0.9) loss_fn = nn.CrossEntropyLoss() for epoch in range(2): running_loss = 0 for i, data in enumerate(test_loader, 0): images, labels = data outputs = model(images) loss = loss_fn(outputs, labels) optimiser.zero_grad() loss.backward() optimiser.step() running_loss += loss.item() print(i) if i % 2000 == 1999: # print every 2000 mini-batches print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000)) running_loss = 0
Sorry, I had to post the entire code because I cannot spot the mistake I made. Moreover, since I could not make it work, I tried copying the tutorial’s exact code, and it works as intended! I am posting that code too below,
import torch import torchvision import torchvision.transforms as transforms transform = transforms.Compose( [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2) testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform) testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2) classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck') import torch.nn as nn import torch.nn.functional as F class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(3, 6, 5) self.pool = nn.MaxPool2d(2, 2) self.conv2 = nn.Conv2d(6, 16, 5) self.fc1 = nn.Linear(16 * 5 * 5, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 10) def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = x.view(-1, 16 * 5 * 5) x = F.relu(self.fc1(x)) x = F.relu(self.fc2(x)) x = self.fc3(x) return x net = Net() import torch.optim as optim criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) for epoch in range(2): # loop over the dataset multiple times running_loss = 0.0 for i, data in enumerate(trainloader, 0): # get the inputs; data is a list of [inputs, labels] inputs, labels = data # zero the parameter gradients optimizer.zero_grad() # forward + backward + optimize outputs = net(inputs) loss = criterion(outputs, labels) loss.backward() optimizer.step() # print statistics running_loss += loss.item() if i % 2000 == 1999: # print every 2000 mini-batches print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000)) running_loss = 0.0 print('Finished Training')
Please help me find the bug!
Advertisement
Answer
Look at your main loop. you’ll notice you are using the test_loader
instead of train_loader
.
This
for epoch in range(2): running_loss = 0 for i, data in enumerate(test_loader, 0): images, labels = data outputs = model(images)
should look like this:
for epoch in range(2): running_loss = 0 for i, data in enumerate(train_loader, 0): images, labels = data outputs = model(images)