Open adriengoleb opened 1 year ago
hi, same problem occurring here. any progress?
form the ' log_vars[loss_name] = loss_value.item()'
,i think it happens for the wrong index labels in the dataset enhancing process.
checking you labels:
as for custom dataset, and not ignoring the background, for padding process, adding another index for the padding elements in case conflicting with the ids would be calculated in you loss function.
for example: for custom dataset, an very common reason for this error is setting the wrong value for padding elements, and solving by : the dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=255) -> dict(type='Pad', size=crop_size, pad_val=0, seg_pad_val=-100),
Hello,
I want to run the training code as follow with 1 GPU :
python tools/train.py local_configs/segformer/B1/segformer.b1.1024x1024.city.160k.py --gpus 1
Firstly, I got the error
AssertionError: Default process group is not initialized
. I followed the others comments by replacing all SyncBN with BN in the code.After that, I obtain this error :
Same error when I launch the command
tools/dist_train.sh local_configs/segformer/B1/segformer.b1.1024x1024.city.160k.py 1
withdist_train.sh
I always obtain this
CUDA error: an illegal memory access was encountered
...