jessemelpolio / Faster_RCNN_for_DOTA

Code used for training Faster R-CNN on DOTA
https://arxiv.org/abs/1711.10398
Apache License 2.0
336 stars 102 forks source link

I can't run the code successfully following the readme.md #28

Closed gxwangupc closed 5 years ago

gxwangupc commented 5 years ago

Hi, I confront the following issue when executing"python experiments/faster_rcnn/rcnn_dota_quadrangle_e2e.py --cfg experiments/faster_rcnn/cfgs/DOTA_quadrangle.yaml"

Traceback (most recent call last): File "experiments/faster_rcnn/rcnn_dota_quadrangle_e2e.py", line 23, in train_quadrangle_end2end.main() File "experiments/faster_rcnn/../../faster_rcnn/train_quadrangle_end2end.py", line 165, in main config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step) File "experiments/faster_rcnn/../../faster_rcnn/train_quadrangle_end2end.py", line 74, in train_net for image_set in image_sets] File "experiments/faster_rcnn/../../faster_rcnn/../lib/utils/load_data.py", line 18, in load_quadrangle_gt_roidb roidb = imdb.gt_roidb() File "experiments/faster_rcnn/../../faster_rcnn/../lib/dataset/DOTA.py", line 291, in gt_roidb gt_roidb = [self.load_annotation(index) for index in self.image_set_index] File "experiments/faster_rcnn/../../faster_rcnn/../lib/dataset/DOTA.py", line 350, in load_annotation cls = class_to_index[obj[8].lower().strip()] KeyError: 'turntable'

I have not found a solution, and could someone help me with it?