Zhao (Dylan) Wang
Zhao (Dylan) Wang
> > What is your result? > > Hello, > > The test result is submitted in the codalab > > lesion_dice_global: 0.732 > > lesion_dice: 0.76 > > lesion_dice_per_case:...
> Initialize the running_corrects to 0.0 instead of 0 in the function train_model in file tars/tars_training.py I have tried your method, but it didn't work, either
> > Initialize the running_corrects to 0.0 instead of 0 in the function train_model in file tars/tars_training.py > > I have tried your method, but it didn't work, either I...
Thanks for response! I would like to further learn if using torch implementation for comparing efficiency is fair?
Thanks for your comment! yes, I have an embedding and a label for each pixel in the image. Meanwhile, total classes is `5`. batch_size is `4` the embedding shape is...
Thanks very much for help! As you have said, I run out of memory. but I meet this problem when trying randomly sampling a reasonable number of triplets. > Traceback...
Thanks a lot! I have sampled pixels randomly for training. But it seems not work. Looking forward to your repo update!
Hi dear author, have this issue updated recently?
Could you provide OLN-Mask pretrained model?