Open Easyfeng222 opened 5 years ago
I am very interested in how you get vg_attr_frequency_1000.pkl. Can you tell me how to get it from the VG dataset? thank you very much! ! @chanyn
In brief, we sum each object attribute annotation of entire dataset if the class of object is in the top 1000 frequent categories we had defined, so we get a 1000D frequency statistic matrix. For relationship frequency statistic matrix, we first new a 1000x1000 zero matrix Qr. Then we check the ground-truth of each relationship annotation and add 1 to the corresponding position of Qr, if both classes are in the range of top 1000 frequent categories. Qr is vg_pair_frequency_1000.pkl that we have provided. For attribute frequency statistic matrix, we new a 1000x200 zero matrix Qa. We just consider top 200 frequent attribute in VG. Then we check the gt annotation of each object and add 1 to the corresponding position of Qa. It's similar to build Qr. Finally, Qa is vg_attr_frequency_1000.pkl.
@chanyn I am sorry to see and express my thanks so late. I still have a problem, I want to rebuild a database training, how can I get gt, coco gt is invalid.
Excuse me ,How can I make vg_attr_frequency_1000.pkl and vg_pair_frequency_1000.pkl?