When i try to train a teacher model resnet50 on new dataset(cub200), the backbone is different with origin resnet50. one the one hand, it is too big to use big batchsize(8 is ok on 16g gpu), on the other hand, the acc1 is too low when i train 300epoch which is 10% . why?
When i try to train a teacher model resnet50 on new dataset(cub200), the backbone is different with origin resnet50. one the one hand, it is too big to use big batchsize(8 is ok on 16g gpu), on the other hand, the acc1 is too low when i train 300epoch which is 10% . why?