Results much better than reported in the paper

[vguptai]

Hi,

Thanks for sharing this amazing work !

This is not an issue but I just wanted to confirm if anyone else is also getting very good results on Gender Identification while training/testing over only fold-0 or I am making some mistake here.

I am getting around 91.5% accuracy without making any change in the training process. Ran the following command after replacing the paths correctly. python train.py --train_dir /home/dpressel/dev/work/AgeGenderDeepLearning/Folds/tf/gen_test_fold_is_0 --max_steps 30000 --eta 0.001

gender_dataset_prepared//run-7274/checkpoint-22000
128 11
2017-07-22 11:44:16.598992 (42.1 examples/sec; 3.042 sec/batch)
2017-07-22 11:44:19.379264 (46.1 examples/sec; 2.779 sec/batch)
2017-07-22 11:44:22.162947 (46.0 examples/sec; 2.783 sec/batch)
2017-07-22 11:44:24.612090 (52.3 examples/sec; 2.449 sec/batch)
2017-07-22 11:44:27.203950 (49.4 examples/sec; 2.591 sec/batch)
2017-07-22 11:44:29.621074 (53.0 examples/sec; 2.417 sec/batch)
2017-07-22 11:44:32.063554 (52.4 examples/sec; 2.442 sec/batch)
2017-07-22 11:44:34.589392 (50.7 examples/sec; 2.526 sec/batch)
2017-07-22 11:44:37.128826 (50.4 examples/sec; 2.539 sec/batch)
2017-07-22 11:44:39.553517 (52.8 examples/sec; 2.425 sec/batch)
2017-07-22 11:44:41.902865 (54.5 examples/sec; 2.349 sec/batch)
2017-07-22 11:44:41.903033: precision @ 1 = 0.915 (1288/1408)
2017-07-22 11:44:41.903047: precision @ 2 = 1.000 (1408/1408)

[red010182]

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

[wbxsdllg]

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 .

[vikram-gupta]

@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

[vikram-gupta]

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

[wbxsdllg]

OK thank you ! @vgupta-ai

[wbxsdllg]

thank you I have solved this problem

[Jason-xin]

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