I am using PyTorch in my program(Binary Classification).
The output from my model and actual labels are
model outputs are: (tensor([[0.4512],
[0.2273],
[0.4710],
[0.2965]], grad_fn=<SigmoidBackward0>), torch.float32),
actuall labels are (tensor([[0],
[1],
[0],
[1]], dtype=torch.int8), torch.int8)
When I calculate the Binary Cross Entropy, it gives me the error
RuntimeError: Found dtype Char but expected Float
I have no idea how it is finding the Char dtype.
Even If calculate it manually, it gives me this error.
import torch cri = torch.nn.BCELoss() cri(torch.tensor([[0.4470],[0.5032],[0.3494],[0.5057]], dtype=torch.float), torch.tensor([[0],[1],[0],[0]], dtype=torch.int8))
My DataLoader is
# CREATING DATA LOADER
class MyDataset(torch.utils.data.Dataset):
def __init__(self, dataframe, subset='train'):
self.subset = subset
self.dataframe = dataframe
self.transforms = transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.Grayscale(),
transforms.ToTensor(),
transforms.Normalize((0.5), (0.5))
])
def __len__(self):
return len(self.dataframe)
def __getitem__(self, index):
row = self.dataframe.iloc[index]
img = Image.open(os.path.join('/kaggle/input/mura-v11',row['path']))
if self.subset=='train':
# print(torch.tensor(0, dtype=torch.int8) if row['labels'] == 'negative' else torch.tensor(1, dtype=torch.int8))
return (self.transforms(img), torch.tensor(0, dtype=torch.int8) if row['labels'] == 'negative' else torch.tensor(1, dtype=torch.int8))
else:
tensor_img = torchvision.transforms.functional.to_tensor(img)
return (tensor_img, torch.tensor(0, dtype=torch.int8) if row['labels'] == 'negative' else torch.tensor(1, dtype=torch.int8))
my training loop is
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(f'Epoch {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)
print(f"model outputs are: {outputs, outputs.dtype}, nmodel labels are {labels.view(labels.shape[0],1), labels.dtype}")
loss = criterion(outputs, labels.view(labels.shape[0], 1))
# 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(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')
# 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(f'Training complete in {time_elapsed // 60:.0f}m {time_elapsed % 60:.0f}s')
print(f'Best val Acc: {best_acc:4f}')
# load best model weights
model.load_state_dict(best_model_wts)
return model
And my Model is
class MuraModel(torch.nn.Module):
def __init__(self):
"""
In the constructor we instantiate four parameters and assign them as
member parameters.
"""
super().__init__()
self.inp = torch.nn.Conv2d(1, 3, 3) # Change the num of channels to 3
self.backbone = models.resnet18(pretrained=True)
num_ftrs = self.backbone.fc.in_features
self.backbone.fc = nn.Linear(num_ftrs, 1)
self.act = nn.Sigmoid()
def forward(self, x):
"""
In the forward function we accept a Tensor of input data and we must return
a Tensor of output data. We can use Modules defined in the constructor as
well as arbitrary operators on Tensors.
"""
three_channel = self.inp(x)
back_out = self.backbone(three_channel)
return self.act(back_out)
# inp = nn.Conv2d(1, 3, 3)
# model_ft = models.resnet18(pretrained=True)(inp)
# num_ftrs = model_ft.fc.in_features
# model_ft.fc = nn.Linear(num_ftrs, 2)
# model_ft = model_ft.to(device)
criterion = nn.BCELoss()
model = MuraModel()
optimizer_ft = optim.SGD(model.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 = train_model(model, criterion, optimizer_ft, exp_lr_scheduler,
num_epochs=25)
How to overcome it.
EDIT
Trace back on train_model function:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
/tmp/ipykernel_17/2718774237.py in <module>
1 model = train_model(model, criterion, optimizer_ft, exp_lr_scheduler,
----> 2 num_epochs=25)
/tmp/ipykernel_17/2670448577.py in train_model(model, criterion, optimizer, scheduler, num_epochs)
33 _, preds = torch.max(outputs, 1)
34 print(f"model outputs are: {outputs, outputs.dtype}, nmodel labels are {labels.view(labels.shape[0],1), labels.dtype}")
---> 35 loss = criterion(outputs, labels.view(labels.shape[0], 1))
36
37 # backward + optimize only if in training phase
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
610
611 def forward(self, input: Tensor, target: Tensor) -> Tensor:
--> 612 return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
613
614
/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py in binary_cross_entropy(input, target, weight, size_average, reduce, reduction)
3063 weight = weight.expand(new_size)
3064
-> 3065 return torch._C._nn.binary_cross_entropy(input, target, weight, reduction_enum)
3066
3067
RuntimeError: Found dtype Char but expected Float
Trace back on calculating loss individually
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
/tmp/ipykernel_17/4156819471.py in <module>
1 import torch
2 cri = torch.nn.BCELoss()
----> 3 cri(torch.tensor([[0.4470],[0.5032],[0.3494],[0.5057]], dtype=torch.float), torch.tensor([[0],[1],[0],[0]], dtype=torch.int8))
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
1108 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1109 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110 return forward_call(*input, **kwargs)
1111 # Do not call functions when jit is used
1112 full_backward_hooks, non_full_backward_hooks = [], []
/opt/conda/lib/python3.7/site-packages/torch/nn/modules/loss.py in forward(self, input, target)
610
611 def forward(self, input: Tensor, target: Tensor) -> Tensor:
--> 612 return F.binary_cross_entropy(input, target, weight=self.weight, reduction=self.reduction)
613
614
/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py in binary_cross_entropy(input, target, weight, size_average, reduce, reduction)
3063 weight = weight.expand(new_size)
3064
-> 3065 return torch._C._nn.binary_cross_entropy(input, target, weight, reduction_enum)
3066
3067
RuntimeError: Found dtype Char but expected Float
Advertisement
Answer
BCELoss() expects float labels. Yours are int8 (aka char). Converting them to float in the last line of__getitem__()should fix the issue.