chengyu0910
chengyu0910
> yes, I found this problem too, it beyonds k-shot instance.
> Hi, > > Thanks for releasing your code/data. Just wondering is the voc_2007_shots file published anywhere? I have the same question. In second training phase, voc_2007_shots is used as...
> Hi, > > Thanks for releasing your code/data. Just wondering is the voc_2007_shots file published anywhere? oh, I found it. The shot files is generated in MetaDataset.get_prndata()
> #5 You can use 5_voc_part.py and 6_voc_few_shot.py to generate the final_split_voc_10_shot_instances_train2017.json. But it is different from the version in the github which is manually picked based on the generated...
there is no comments in codes , it is hard to understand what is done.
> Hi, have you got the trained model of the authors? > Thank you for your contribution to the field of SBIR. I down ShoeV2 and ChairV2 from http://sketchx.eecs.qmul.ac.uk/downloads/ ，but...
> Hi, thanks for your interest in this work. > > Specifically, a table is created before training to list the ids of all images which have at least an...
> the sampling is complicated, yet the way I implemented it inside this repository coul Hi, I read the code. You use the 'rng_same' mode to sample novel examples. So,...
> I totally agree, I actually conducted some experiments about it and it does hurt the performance. I think it is a better choice to keep all annotations for the...