Open Malatan opened 7 months ago
And I also trained the model using: --train=True --net_arch=vgg19 --double_stream_mode=True --epoch_num=10 --batch_size=10 --cls_num=16 --learning_rate=1e-4 --shuffle_dataset=True --img_list1=train_test_eval_splits\annotator_consistency3\single_body1_train_16 --img_list2=train_test_eval_splits\annotator_consistency3\single_body2_train_16 Is this correct? I also read in the paper that you used different attributes like age, gender, clothing etc.. for the recognition but I can't find part that is related to this in the code.
I realized that 'single_face1_train_16.txt' is missing in the train_test_eval_splits folder which is downloaded in splits.