question about cosineCE

[Z-ZHHH]

I have run the CIFAR-100-Imb100 experiment_no=0.2, i got this results which is different from that in the paper.

CIFAR100	Imb100	val-toatal	val-many	val-med	val-few
Seed1	CosineCE	0.403	0.676	0.379	0.112
Seed2	CosineCE	0.403	0.670	0.396	0.101
Seed3	CosineCE	0.405	0.680	0.380	0.113
Seed10	CosineCE	0.4051	0.6737	0.3923	0.1067
Seed20	CosineCE	0.3968	0.6754	0.3909	0.7867
Seed30	CosineCE	0.4045	0.6811	0.378	0.1127

[Angelina1996]

Hi Z-ZHHH, could you please guide how did you execute the code, for me it is generating an error with the following error.
with open('default_config.yaml') as f:
FileNotFoundError: [Errno 2] No such file or directory: 'default_config.yaml'.
In fact, default_config.yaml file is present in the current directory.
Cheers,
Angelina

[rahulvigneswaran]

@Z-ZHHH Sorry about the super delayed reply. We faced similar issues when replicating other paper results too. The cifar100-lt is sketchy and the final results seem very sensitive to randomness. To combat this, we recommend you to use the saved data_target tuples at https://github.com/rahulvigneswaran/TailCalibX/tree/master/libs/data/CIFAR100_LT

[rahulvigneswaran]

@Angelina1996 Are you still facing this issue?