Hi, I am trying to make a model to classify knee MRIs. I am using the torchio library and I have succesfully train a classifier to the raw data. Now, I am adding masks to the MRI object and I want to pass them to a model. I use the same code but now I am getting this error:
RuntimeError Traceback (most recent call last)
<ipython-input-56-2a7d5ddf84fc> in <module>()
26 for epoch in range(1, num_epochs+1):
27
---> 28 train_loss, train_accuracy = training(epoch,model,train_loader,optimizer,criterion)
29 valid_loss, valid_accuracy = validation(epoch,model,valid_loader,criterion)
30
6 frames
<ipython-input-55-59a55a26f2b7> in training(epoch, model, train_loader, optimizer, criterion)
8 model.train()
9
---> 10 for i, batch in tqdm(enumerate(train_loader,0)):
11 images = batch['t1'][tio.DATA].cuda()
12 labels = batch['label']
/usr/local/lib/python3.7/dist-packages/tqdm/notebook.py in __iter__(self)
255 def __iter__(self):
256 try:
--> 257 for obj in super(tqdm_notebook, self).__iter__():
258 # return super(tqdm...) will not catch exception
259 yield obj
/usr/local/lib/python3.7/dist-packages/tqdm/std.py in __iter__(self)
1193
1194 try:
-> 1195 for obj in iterable:
1196 yield obj
1197 # Update and possibly print the progressbar.
/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py in __next__(self)
519 if self._sampler_iter is None:
520 self._reset()
--> 521 data = self._next_data()
522 self._num_yielded += 1
523 if self._dataset_kind == _DatasetKind.Iterable and \
/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py in _next_data(self)
1201 else:
1202 del self._task_info[idx]
-> 1203 return self._process_data(data)
1204
1205 def _try_put_index(self):
/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py in _process_data(self, data)
1227 self._try_put_index()
1228 if isinstance(data, ExceptionWrapper):
-> 1229 data.reraise()
1230 return data
1231
/usr/local/lib/python3.7/dist-packages/torch/_utils.py in reraise(self)
432 # instantiate since we don't know how to
433 raise RuntimeError(msg) from None
--> 434 raise exception
435
436
RuntimeError: Caught RuntimeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py", line 52, in fetch
return self.collate_fn(data)
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in <dictcomp>
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 74, in <dictcomp>
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/collate.py", line 56, in default_collate
return torch.stack(batch, 0, out=out)
**RuntimeError: result type Float can't be cast to the desired output type Byte**
The training() function is this:
def training(epoch, model, train_loader, optimizer, criterion):
"Training over an epoch"
metric_monitor = MetricMonitor()
model.train()
for i, batch in tqdm(enumerate(train_loader,0)):
images = batch['t1'][tio.DATA].cuda()
labels = batch['label'].cuda()
if images.sum() != 0:
output = F.softmax(model(images), dim =1)
loss = criterion(output, labels)
output = output.data.max(dim=1,keepdim=True)[1]
output = output.view(-1)
acc = calculate_acc(output, labels)
metric_monitor.update("Loss", loss.item())
metric_monitor.update("Accuracy", acc)
optimizer.zero_grad()
loss.backward()
optimizer.step()
print("[Epoch: {epoch:03d}] Train | {metric_monitor}".format(epoch=epoch, metric_monitor=metric_monitor))
return metric_monitor.metrics['Loss']['avg'], metric_monitor.metrics['Accuracy']['avg']
When I run the code some batches pass but it stops on some batches and produces this error. I have checked my data and all of them are torch.FloatTensor
The labels are integers.