Need help regarding Transfer Learning a Faster RCNN ResNet50FPN in PyTorch - python-3.x

Question

I am new to PyTorch. I'm trying to use a pre-trained Faster RCNN torchvision.models.detection.fasterrcnn_resnet50_fpn() for object detection project. I have created a CustomDataset(Dataset) class to handle the custom dataset.
Here is the custom class implementation
class ToTensor(object):
"""Convert ndarrays in sample to Tensors."""
def __call__(self, sample):
image, landmarks = sample['image'], sample['meta_data']
# swap color axis because
# numpy image: H x W x C
# torch image: C X H X W
image = image.transpose((2, 0, 1))
return {'image': torch.from_numpy(image),
'meta_data': landmarks}
class CustomDataset(Dataset):
"""Custom Landmarks dataset."""
def __init__(self, data_dir, root_dir, transform=None):
"""
Args:
data_dir (string): Directory with all the labels(json).
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.data_dir = data_dir
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(os.listdir(self.data_dir))
def __getitem__(self, idx):
img_name = sorted(os.listdir(self.root_dir))[idx]
image = io.imread(self.root_dir+'/'+img_name, plugin='matplotlib')
json_file = sorted(os.listdir(self.data_dir))[idx]
with open(self.data_dir+'/'+json_file) as f:
meta_data = json.load(f)
meta_data = meta_data['annotation']['object']
sample = {'image': image, 'meta_data': meta_data}
to_tensor = ToTensor()
transformed_sample = to_tensor(sample)
if self.transform:
sample = self.transform(sample)
return transformed_sample
Here is the train_model function
def train_model(model, criterion, optimizer, lr_scheduler, num_epochs=25):
since = time.time()
best_model = model
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', 'test']:
if phase == 'train':
optimizer = lr_scheduler(optimizer, epoch)
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
running_loss = 0.0
running_corrects = 0
for data in dset_loaders[phase]:
# get the inputs
inputs, labels = data['image'], data['meta_data']
inputs= inputs.to(device) # ,
# zero the parameter gradients
optimizer.zero_grad()
# forward
outputs = model(inputs, labels)
_, preds = torch.max(outputs.data, 1)
loss = criterion(outputs, labels)
# backward + optimize only if in training phase
if phase == 'train':
loss.backward()
optimizer.step()
# statistics
running_loss += loss.item()
running_corrects += torch.sum(preds == labels).item()
epoch_loss = running_loss / dset_sizes[phase]
epoch_acc = running_corrects / dset_sizes[phase]
print('{} Loss: {:.4f} Acc: {:.4f}'.format(
phase, epoch_loss, epoch_acc))
# deep copy the model
if phase == 'test' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model = copy.deepcopy(model)
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))
return best_model
While performing model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, num_epochs=25) I am getting "RuntimeError: _thnn_upsample_bilinear2d_forward not supported on CUDAType for Byte"

Answer 1

It appears your datapoints are byte tensors, i.e type uint8. Try casting your data into float32
# Replace this
inputs = inputs.to(device)
# With this
inputs = inputs.float().to(device)
Note that the torchvision models expect data to be normalized in a specific way. Check here for the procedure, which basically entails using
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
for normalizing your data.