search

stevehuanghe / GDAN

Generative Dual Adversarial Network for Generalized Zero-shot Learning
MIT License
53 stars 12 forks source link

Train_loc, val_loc, and trainval_loc #5

Open sangrockEG opened 4 years ago

sangrockEG commented 4 years ago

I downloaded xlsa17 proposed split dataset to test CUB. But att_mat does not contain neither train_loc or val_loc keys. It only includes trainval_loc. Funny thing is, in standard split, there exists train_loc and val_loc. Is it intended?

jwliu-cc commented 4 years ago

I've got the same problem. And I extracted train_loc and val_loc from trainval_loc according to "trainclasses.txt" and "valclasses.txt". But the result is not so good, especially at test_seen.

sangrockEG commented 4 years ago

I did not test with train/val split of trainval class, so thanks for your comment. Is your result much worse than the result of paper? It's really weird.. may only the authors can help us.

jwliu-cc commented 4 years ago

The 'gzsl unseen' is 34. while it is 39.3 in the paper. And the 'gzsl seen' is only 26. while it is 66.7 in the paper. The classifier is knn so I even try to train knn with trainval_loc and test with test_seen, but it only got 47. I'm very confused...

lixiaorui4444 commented 4 years ago

The dataset CADA-VAE provides works well.