Results much better than reported in the paper about rude-carnie HOT 7 CLOSED

I don't see tf in Folds in https://github.com/GilLevi/AgeGenderDeepLearning, where did u find the model?

from rude-carnie.

hi
when I run
python preproc.py --fold_dir /Users/ca/Desktop/ca/rude-carnie/AgeGenderDeepLearning/Folds/train_val_txt_files_per_fold/test_fold_is_0 --train_list age_train.txt --valid_list age_val.txt --data_dir /Users/ca/desktop/ca/rude-carnie/8-12 --output_dir /Users/ca/Desktop/ca/rude-carnie/AgeGenderDeepLearning/Folds/tf/age_test_fold_is_0
I find that the doc of age_test_fold_is_0 is empty.
@vgupta-ai
I think that it is the problem of ' --data_dir /data/xdata/age-gender/aligned' .
I don't know how to alter this .
should I download the dataset face.tar.gz and aligned.tar.gz is the ( /data/xdata/age-gender/aligned) is in them?
please tell me how can I alter this .

from rude-carnie.

@red010182 you have to preprocess your data which would create the shards for the dataset with something like the following command and then use the folder in which the shards got created.

python preproc.py --fold_dir /home/dpressel/dev/work/AgeGenderDeepLearning/Folds/train_val_txt_files_per_fold/test_fold_is_0 --train_list age_train.txt --valid_list age_val.txt --data_dir /data/xdata/age-gender/aligned --output_dir /home/dpressel/dev/work/AgeGenderDeepLearning/Folds/tf/age_test_fold_is_0

from rude-carnie.

@wbxsdllg yes, i think so. I downloaded the adience aligned dataset and then ran the preprocessing step.

from rude-carnie.

OK thank you ! @vgupta-ai

from rude-carnie.

thank you I have solved this problem

from rude-carnie.

why close this comment? I met the same question that the result is 91.8%

from rude-carnie.