Regarding torch.utils.data.DataLoader and batch_size

[jjong2ya]

Hi all the high-level engineers!

I am very new to pytorch and even to pythone.
Nonetheless, I am trying to understand pytorch by the documentation of the tutorial of pytorch.
Now I am going through TRAINING A CLASSIFIER using dataset, CIFAR10.

Code Link: https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html

In the code, there is the lines as follows;

for i, data in enumerate(trainloader, 0):
inputs, labels=data

I have checked the size of data[0] and input[0], and they are different and it was [4, 3, 32, 32] and [3, 32, 32] respectively.
I understand that data[0] has the size of [4, 3, 32, 32] as it is the first batch that contains 4 images.

Question

1. But why is the size of input[0] [3, 32, 32]? As I checked, input[0] is the first image of the data[0].
   Why is input[0] only taking the first image of data[0]? According to the code, input[0]=data[0], shouldn't it ?

2. According to the tutorial, "data is a list of [inputs, labels]". But I don't see labels[0] value in data[0].
   Why is so?

Sorry if it is too basic, but please help.

[jjong2ya]

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 matplotlib.pyplot as plt
import numpy as np

functions to show an image

def imshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))

get some random training images

dataiter = iter(trainloader)
images, labels = dataiter.next()

show images

imshow(torchvision.utils.make_grid(images))

print labels

print(' '.join('%5s' % classes[labels[j]] for j in range(4)))

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
    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')

dataiter = iter(testloader)
images, labels = dataiter.next()

print images

imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))

outputs = net(images)

_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
for j in range(4)))

correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
for data in testloader:
images, labels = data
outputs = net(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(4):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1

for i in range(10):
print('Accuracy of %5s : %2d %%' % (
classes[i], 100 * class_correct[i] / class_total[i]))

[holly1238]

Closing this as it is more than a year old. If you are still having trouble, feel free to reopen this or open a new issue. You can also post your question in our PyTorch discussion forum where you'll get a quick response from our skilled community members (https://discuss.pytorch.org/).