Closed Wei-i closed 2 years ago
Another issue made me confused is that how I can new a DCNet/fs_list/voc_traindict_bbox_Xshot.txt
and DCNet/fs_list/voc_traindict_full.txt
instead of using the files you provide in which each line contains the absolute path.
When preparing voc_dataset, the dir is 'datasets/VOCdevkit/..', however when training, the root_dir
is datasets/voc/VOC{year}
and so on .
BTW, these made me feel sad to reproduce by my poor ability.
voc_split_3_base_training:
reproduce reuslt: voc_split_1_10_shot: 58.9 vs 59.6(from the paper) voc_split_2_10_shot: 44.9 vs 46.6(from the paper)
Thank you for the reminder. I have updated the code.
For the performance in the paper, we report the results averaged over multiple random runs.
https://github.com/hzhupku/DCNet/blob/a73f448fc664d8c5aabf8b7b459942e8c576e6a6/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py#L47