Chauncy-Cai

It seems training pixelsnail (both top and bottom) take much longer than than train vqvae. 44min for every epoch. I don't know whether it is normal. Moreover, is there anyone...

 Maybe this yaml may help. Because of such few instances and early-stop strategy to prevent overfitting, the unstable result is normal.

> @yhcao6 Seems odd. I would say above 62.6 should be easy to reach.  This is my rerun today. It does reach 62.5+ without any change. Since few-shot task...

> What does seed0 mean? In http://dl.yf.io/fs-det/datasets/vocsplit/, there no seed0 folder. OK,I should describe more accurately. "http://dl.yf.io/fs-det/datasets/vocsplit/*.txt" instead of "seed0". >  >  > > In Table1, the performance...

Just simply train the code with data in "seeds [1-10]" files in "http://dl.yf.io/fs-det/datasets/vocsplit/". You can change the train&test dataset in yaml directly. For instance, (coco_trainval_all_30shot) ->(coco_trainval_all_30shot_seed1) to use seed1 file.

I try your cmd myself, and it works normally. Please check your code carefully or provide more information.

I have a similar problem, my cls_acc is not 0% but just around 15~20%. The same thing is my recall and precision remain 0 after 4k steps, while loss seems...

I want that annotation file, too. Thanks

另，是否可以允许用户自由选择是否使用AI。 这样可以用户更能感受到AI对效果的提升。