worse precision and recall results

[B-Alkan]

Hi,
I've been trying your models on different test sets for a while. Even though i used FVC 2002, 2004 test set, performance results are worse than indicated on the paper. I have fine-tuned the model but still can not reached specified results. Are the models (Coarsenet and Finenet) same as indicated on the paper? Network is using too much memory, while fine-tuning with batch size bigger than 2 i got resource exhausted error on 16 gb Tesla V100 GPU. How did you deal with it?

[peterlo12]

Recently I also tested the models on FVC datasets. The results are worse than the results mentioned in the paper. I talked to a few people who tested also. Non of them could achieve the results as paper indicated. I also wonder the models are the same as indicated in the paper.