Hi There,
I’m trying to build an image classifier but there seems to be a persistent issue of memory filling. As soon as I execute this function, the memory starts to fill up and before it’s epoch 2, the kernel crashes.
The following is the training function:
def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False):
since = time.time()
val_acc_history = []
print("Device = ", device)
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs):
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 10)
# Each epoch has a training and validation phase
for phase in ['train', 'val']:
if phase == 'train':
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
# Iterate over data.
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device)
labels = labels.to(device)
# zero the parameter gradients
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
# Get model outputs and calculate loss
# Special case for inception because in training it has an auxiliary output. In train
# mode we calculate the loss by summing the final output and the auxiliary output
# but in testing we only consider the final output.
if is_inception and phase == 'train':
# From https://discuss.pytorch.org/t/how-to-optimize-inception-model-with-auxiliary-classifiers/7958
outputs, aux_outputs = model(inputs)
loss1 = criterion(outputs, labels)
loss2 = criterion(aux_outputs, labels)
loss = loss1 + 0.4*loss2
else:
outputs = model(inputs)
loss = criterion(outputs, labels)
optimizer.zero_grad()
_, preds = torch.max(outputs, 1)
del inputs
del labels
# backward + optimize only if in training phase
if phase == 'train':
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item() * inputs.size(0)
running_corrects += torch.sum(preds == labels.data)
loss.detach()
epoch_loss = running_loss / len(dataloaders[phase].dataset)
epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)
print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == 'val' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
if phase == 'val':
val_acc_history.append(epoch_acc)
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
# load best model weights
model.load_state_dict(best_model_wts)
return model, val_acc_history
Then I print some parameters and move the model to GPU
model_ft, input_size = initialize_model(model_name, n_classes, use_pretrained = True)
# Move Model To GPU
model_ft = model_ft.to(device)
print("Params to learn:")
params_to_update = model_ft.parameters()
for name,param in model_ft.named_parameters():
if param.requires_grad == True:
print("\t",name)
optimizer_ft = optim.Adam(params_to_update, learning_rate)
criterion = nn.CrossEntropyLoss()
Using the very function defined above, I train this model, which then crashes my kernel.
trained_model, hist = train_model(model_ft, dataloaders, criterion, optimizer_ft, num_epochs = epochs)
print(model_ft)
Please tell me if further information is required so I can get this issue resolved.
Thanks in advance.