I an trying to fine tune the fcn_resnet101 segmentation model with my own data and I am getting AttributeError: 'collections.OrderedDict' object has no attribute 'log_softmax'
error when I run my code.
Below is a full print out of the error:
model_ft, hist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))
File "FineTuningTry1.py", line 266, in train_model
loss = criterion(outputs, labels.long())
File "/home/info/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 547, in __call__
result = self.forward(*input, **kwargs)
File "/home/info/.local/lib/python3.5/site-packages/torch/nn/modules/loss.py", line 916, in forward
ignore_index=self.ignore_index, reduction=self.reduction)
File "/home/info/.local/lib/python3.5/site-packages/torch/nn/functional.py", line 1995, in cross_entropy
return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
File "/home/info/.local/lib/python3.5/site-packages/torch/nn/functional.py", line 1316, in log_softmax
ret = input.log_softmax(dim)
AttributeError: 'collections.OrderedDict' object has no attribute 'log_softmax'
It seems like the error is happening when calculating the loss with the criterion function, but I am not sure what to make of the ‘log_softmax’ error to try to find where I went wrong with my code.
Below is the code for the train_model function that I adjusted from this tutorial:
def train_model(model, dataloaders, criterion, optimizer, num_epochs=25, is_inception=False):
since = time.time()
val_acc_history = []
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
total_train = 0
correct_train = 0
# Iterate over data.
for inputs, labels in dataloaders[phase]:
inputs = inputs.to(device) #OriginalImage
labels = labels.to(device) #Masks
# 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.long())
_, preds = torch.max(outputs, 1)
# backward + optimize only if in training phase
if phase == 'train':
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item() #* inputs.size(0)
total_train += labels.nelement()
correct_train += preds.eq(labels.data).sum().item()
train_accuracy = 100 * correct_train / total_train
epoch_loss = running_loss / len(dataloaders[phase].dataset)
epoch_acc = train_accuracy/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
and below is the part where I set the criterion and call the train_model function:
# Setup the loss fxn
criterion = nn.CrossEntropyLoss()
# Train and evaluate
model_ft, hist = train_model(model_ft, dataloaders_dict, criterion, optimizer_ft, num_epochs=num_epochs, is_inception=(model_name=="inception"))
If this isn’t enough information to help me figure out why I am getting this error, let me know and I’ll post other parts of my code. I just didn’t want to fill this post with unnecessary code. Appreciate your help!