I am training a simple conv layer on cifar10 and I keep getting a high loss during training:
Epoch 1/50 - Training loss: nan
Epoch 2/50 - Training loss: nan
Conv Network
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.conv3 = nn.Conv2d(16, 32, 5)
self.conv4 = nn.Conv2d(32, 64, 5)
self.conv5 = nn.Conv2d(64, 64, 1)
self.fc1 = nn.Linear(64 * 1 * 1, 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 = F.relu(self.conv2(x))
#print(x.shape)
x = F.relu(self.conv3(x))
x = F.relu(self.conv4(x))
x = self.pool(F.relu(self.conv5(x)))
x = x.view(-1, 64 * 1 * 1)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
Here are the training and validation functions:
def train_conv(model):
minimum = 1000
model = model.cuda()
optimizer = optim.SGD(model.parameters(), lr=0.003, momentum=0.9)
criterion =nn.NLLLoss()
epochs = 50
for epoch in range(epochs): # loop over the dataset multiple times
running_loss = 0.0
for inputs, labels in train_loader:
# get the inputs; data is a list of [inputs, labels]
inputs, labels = inputs.cuda(),labels.cuda()
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = model(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / len(train_loader)))
return (running_loss/len(train_loader))
def validation_conv(model):
correct = 0
total = 0
model = model.cuda()
with torch.no_grad():
for data in val_loader:
images, labels = data
images, labels = images.cuda(),labels.cuda()
outputs = model(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))
I am not sure how to change the train_conv function to get the correct training loss.