I am working on training a CNN with transfer learning on resnet50. My script was working until I made some modifications. I manually split my dataset into train and validation folders. And I setup weights on the training dataset since it was unbalanced. I am receiving an error when I run the training. Here is my code and the error:
train_data_dir = '/home/ec2-user/SageMaker/data/frame_150/train'
val_data_dir = '/home/ec2-user/SageMaker/data/frame_150/val'
batch_size = 100
data_transforms = {
'train': transforms.Compose([transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])]),
'val': transforms.Compose([transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
}
image_datasets = {'train': datasets.ImageFolder(train_data_dir, data_transforms['train']),
'val': datasets.ImageFolder(val_data_dir, data_transforms['val'])
}
def make_weights_for_balanced_classes(images, nclasses):
count = [0] * nclasses
for item in images:
count[item[1]] += 1
weight_per_class = [0.] * nclasses
N = float(sum(count))
for i in range(nclasses):
weight_per_class[i] = N/float(count[i])
weight = [0] * len(images)
for idx, val in enumerate(images):
weight[idx] = weight_per_class[val[1]]
return weight
weights = make_weights_for_balanced_classes(image_datasets['train'].imgs, len(image_datasets['train'].classes))
weights = torch.DoubleTensor(weights)
sampler = torch.utils.data.sampler.WeightedRandomSampler(weights, len(weights))
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=batch_size, sampler=sampler, num_workers=4) for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
since = time.time()
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'):
outputs = model(inputs)
_, preds = torch.max(outputs, 1)
loss = criterion(outputs, 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)
if phase == 'train':
scheduler.step()
epoch_loss = running_loss / dataset_sizes[phase]
epoch_acc = running_corrects.double() / dataset_sizes[phase]
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())
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
model_ft = models.resnet50(pretrained=True)
num_ftrs = model_ft.fc.in_features
# Here the size of each output sample is set to 2.
# Alternatively, it can be generalized to nn.Linear(num_ftrs, len(class_names)).
model_ft.fc = nn.Linear(num_ftrs, 2)
model_ft = model_ft.to(device)
criterion = nn.CrossEntropyLoss()
# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)
# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=6)
ERROR:
---------------------------------------------------------------------------
IndexError Traceback (most recent call last)
<ipython-input-29-c677c5f760af> in <module>()
1 model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
----> 2 num_epochs=6)
<ipython-input-26-6f4f613da14c> in train_model(model, criterion, optimizer, scheduler, num_epochs)
20
21 # Iterate over data.
---> 22 for inputs, labels in dataloaders[phase]:
23 inputs = inputs.to(device)
24 labels = labels.to(device)
~/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py in __next__(self)
343
344 def __next__(self):
--> 345 data = self._next_data()
346 self._num_yielded += 1
347 if self._dataset_kind == _DatasetKind.Iterable and \
~/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py in _next_data(self)
854 else:
855 del self._task_info[idx]
--> 856 return self._process_data(data)
857
858 def _try_put_index(self):
~/.local/lib/python3.6/site-packages/torch/utils/data/dataloader.py in _process_data(self, data)
879 self._try_put_index()
880 if isinstance(data, ExceptionWrapper):
--> 881 data.reraise()
882 return data
883
~/.local/lib/python3.6/site-packages/torch/_utils.py in reraise(self)
392 # (https://bugs.python.org/issue2651), so we work around it.
393 msg = KeyErrorMessage(msg)
--> 394 raise self.exc_type(msg)
IndexError: Caught IndexError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/ec2-user/.local/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "/home/ec2-user/.local/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/ec2-user/.local/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 44, in <listcomp>
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/ec2-user/.local/lib/python3.6/site-packages/torchvision/datasets/folder.py", line 137, in __getitem__
path, target = self.samples[index]
IndexError: list index out of range