Why is my loss not decreasing over training 10 epochs? - deep-learning

Question

My hardware is a Ryzen 5000 series cpu with an nvidia rtx 3060 gpu. I'm currently working on a school assignment involving using a deep learning model (implemented in PyTorch) to predict COVID diagnosis from CT slice images. The dataset can be found at this url on GitHub: https://github.com/UCSD-AI4H/COVID-CT
I've written a custom dataset that takes the images from the dataset and resizes them to 224x224. I've also converted all rgba or grayscale images to rgb using skimage.color. Other transforms include random horizontal and vertical flipping, as well as ToTensor(). To evaluate the model I've used sklearn.metrics to compute the AUC, F1 score, and accuracy of the model.
My trouble is that I can't get the model to train. After 10 epochs the loss has not decreased. I've tried adjusting the learning rate of my optimizer but it hasn't helped. Any recommendations/thoughts would be greatly appreciated. Thanks!
class RONANet(nn.Module):
def __init__(self, classifier_type=None):
super(RONANet, self).__init__()
self.classifier_type = classifier_type
self.relu = nn.ReLU()
self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
self.classifier = self.compose_classifier()
self.conv_layers = nn.Sequential(
nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(32),
self.relu,
self.maxpool,
nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(64),
self.relu,
self.maxpool,
nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(128),
self.relu,
self.maxpool,
nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
self.relu,
self.maxpool,
nn.AdaptiveAvgPool2d(output_size=(1,1)),
)
def compose_classifier(self):
if 'fc' in self.classifier_type:
classifier = nn.Sequential(
nn.Flatten(),
nn.Linear(14**2*256, 256),
self.relu,
nn.Linear(256, 128),
self.relu,
nn.Linear(128, 2))
elif 'conv'in self.classifier_type:
classifier = nn.Sequential(
nn.Conv2d(256, 1, kernel_size=1, stride=1))
return classifier
def forward(self, x):
features = self.conv_layers(x)
out = self.classifier(features)
if 'conv' in self.classifier_type:
out = out.reshape([-1,])
return out
RONANetv1 = RONANet(classifier_type='conv')
RONANetv1 = RONANetv1.cuda()
RONANetv2 = RONANet(classifier_type='fc')
RONANetv2 = RONANetv2.cuda()
criterion = nn.BCEWithLogitsLoss()
optimizer = torch.optim.Adam(RONANetv1.parameters(), lr=0.1)
num_epochs = 100
best_auc = 0.5 # set threshold to random model performance
scores = {}
for epoch in range(num_epochs):
RONANetv1.train()
print(f'Current Epoch: {epoch+1}')
epoch_loss = 0
for images, labels in train_dataloader:
batch_loss = 0
optimizer.zero_grad()
with torch.set_grad_enabled(True):
images = images.cuda()
labels = labels.cuda()
out = RONANetv1(images)
loss = criterion(out, labels)
batch_loss += loss.item()
loss.backward()
optimizer.step()
epoch_loss += batch_loss
print(f'Loss this epoch: {epoch_loss}\n')
current_val_auc, current_val_f1, current_val_acc = get_scores(RONANetv1, val_dataloader)
if current_val_auc > best_auc:
best_auc = current_val_auc
torch.save(RONANetv1.state_dict(), 'RONANetv1.pth')
scores['AUC'] = current_val_auc
scores['f1'] = current_val_f1
scores['Accuracy'] = current_val_acc
print(scores)
.
Output:
Current Epoch: 1
Loss this epoch: 38.038745045661926
{'AUC': 0.6632183908045978, 'f1': 0.0, 'Accuracy': 0.4915254237288136}
Current Epoch: 2
Loss this epoch: 37.96312761306763
Current Epoch: 3
Loss this epoch: 37.93656861782074
Current Epoch: 4
Loss this epoch: 38.045261442661285
Current Epoch: 5
Loss this epoch: 38.01626980304718
Current Epoch: 6
Loss this epoch: 37.93017905950546
Current Epoch: 7
Loss this epoch: 37.913547694683075
Current Epoch: 8
Loss this epoch: 38.049841582775116
Current Epoch: 9
Loss this epoch: 37.95650988817215

Answer 1

can you try with this learning rate
optimizer = torch.optim.Adam(RONANetv1.parameters(), lr=0.001)
and probably wait for atleast 25 epochs

Answer 2

So the issue is you're only training the first part of the classifier and not the second
# this
optimizer = torch.optim.Adam(RONANetv1.parameters(), lr=0.1)
# needs to become this
from itertools import chain
optimizer = torch.optim.Adam(chain(RONANetv1.parameters(), RONANetv2.parameters()))
and you need to incorportate the other cnn in training too
intermediate_out = RONANetv1(images)
out = RONANetv2(intermediate_out)
loss = criterion(out, labels)
batch_loss += loss.item()
loss.backward()
optimizer.step()
Hope that helps best of luck!