import torch
import torchvision
import torchvision.transforms as transforms
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self,dev=None):
super().__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)
self.criterion = nn.CrossEntropyLoss()
self.optimizer = optim.SGD(self.parameters(), lr=0.001, momentum=0.9)
if dev:
self.device = torch.device('cpu')
else:
self.device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
print("Device:", self.device)
self.to(self.device)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = torch.flatten(x, 1) # flatten all dimensions except batch
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
def getDataset():
# The transform normalises the dataset
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
batch_size = 4
# We use standard datasets provided by torchvision, in this case CIFAR10
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
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=batch_size,
shuffle=False, num_workers=2)
return (trainloader,testloader)
def evalmodel(net,dataloader):
tloss = 0.0
net.eval()
for i, data in enumerate(dataloader, 0):
inputs, labels = (data[0].to(net.device), data[1].to(net.device))
outputs = net(inputs)
loss = net.criterion(outputs, labels)
tloss += loss.item()
return(tloss/len(dataloader))
def trainmodel(net,dataloader):
running_loss = 0.0
tloss = 0.0
net.train()
for i, data in enumerate(dataloader, 0):
# get the inputs; data is a list of [inputs, labels]
inputs, labels = (data[0].to(net.device), data[1].to(net.device))
# zero the parameter gradients
net.optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = net.criterion(outputs, labels)
loss.backward()
net.optimizer.step()
# print statistics
running_loss += loss.item()
tloss += loss.item()
if i % 2000 == 1999: # print every 2000 mini-batches
print(f'[Training, {i + 1:5d}] loss: {running_loss / 2000:.3f}')
running_loss = 0.0
return(tloss/len(dataloader))
