I am trying to calculate training and validation loss however I am getting an extremely high amount that is not converging
‘’'transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
batch_size = 32
cifar10 = torchvision.datasets.CIFAR10(root=‘./data’, download=True, transform=torchvision.transforms.ToTensor())
pivot = 40000
cifar10 = sorted(cifar10, key=lambda x: x[1])
train_set = torch.utils.data.Subset(cifar10, range(pivot))
val_set = torch.utils.data.Subset(cifar10, range(pivot, len(cifar10)))
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True)
val_loader = DataLoader(val_set, batch_size=batch_size, shuffle=True)‘’’
class Network(nn.Module):
def init(self):
super().init()
#Using padding convolution 2d if downsampling is performed by average pooling
self.conv1 = nn.Conv2d(3, 6, kernel_size = 5, padding = 2)
#MaxPooling2D has no attribute with torch.nn so changed it to MaxPool2d
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, kernel_size = 5, padding = 2)
self.fc1 = nn.Linear(8816, 120)
self.fc2 = nn.Linear(120, 2)
self.fc3 = nn.Linear(2, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
#Flatten has no attribute with torch so changed it to flatten
x = torch.flatten(x, 1)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
model = Network()
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e3, momentum=0.9)
with wandb.init(project = ‘Tier-1-Test’, save_code=True) as run:
for epoch in range(5):
current_loss = 0
model.train()
for i, data in enumerate(train_loader):
images, labels = data
outputs = model(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
current_loss += loss
run.log({'train_loss': current_loss / (i + 1)})
model.eval()
current_loss = 0
for i, data in enumerate(val_loader):
images, labels = data
outputs = model(images)
loss = criterion(outputs, labels)
current_loss += loss
run.log({'val_loss': current_loss / (i + 1)})