I am not understanding what this exception means or how to fix it?
I am building the following convolutional neural network with 3 convolutional layers and 2 fully connected layers:
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
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=0)
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=0)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
# -------------- Define a convolutional neural network (CNN) -------------
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.conv3 = nn.Conv2d(16, 32, 5)
self.fc1 = nn.Linear(32 * 2 * 2, 120)
self.fc2 = nn.Linear(120, 84)
def forward(self, x):
x = self.pool(F.elu(self.conv1(x)))
x = self.pool(F.elu(self.conv2(x)))
x = F.elu(self.conv3(x))
x = x.view(-1, 32 * 2 * 2)
x = F.elu(self.fc1(x))
x = self.fc2(x)
return x
net = Net()
# ------------------------ Define a loss (distance) function and optimizer----------------------
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
# ------------------------ Train the network -------------------------
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')
# ----------- Save model -------------
PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)
But am getting the following error
ValueError: Expected input batch_size (1) to match target batch_size (4).
Any advice is greatly appreciated!
EDIT: I printed the shape of x before my view and discovered it was:
torch.Size([4, 32, 1, 1])
So I changed my linear layer to
self.fc1 = nn.Linear(32 * 1 * 1, 120)
and my view to
x = x.view(-1, 32 * 1 * 1)
and it seemed to train successfully… if someone could please verify this is accurate, I would appreciate it! Thanks for your time reading this