error use containers.Map/values in my datasets

[hongzhangMu]

错误使用 containers.Map/values

出错 roidb_from_voc>attach_proposals (line 172) gt_classes = class_to_id.values({voc_rec.objects(valid_objects).class});

出错 roidb_from_voc (line 130) roidb.rois(i*2-1) = attach_proposals(voc_rec, regions.boxes{i}, imdb.class_to_id, opts.exclude_difficult_samples, false);

出错 Dataset.voc2007_trainval>@(x)x.roidb_func(x) (line 12) dataset.roidb_train = cellfun(@(x) x.roidb_func(x), dataset.imdb_train, 'UniformOutput', false);

出错 Dataset.voc2007_trainval (line 12) dataset.roidb_train = cellfun(@(x) x.roidb_func(x), dataset.imdb_train, 'UniformOutput', false);

出错 script_faster_rcnn_VOC2007_ZF (line 29) dataset = Dataset.voc2007_trainval(dataset, 'train', use_flipped);

[Cogito2012]

You should check your annotation files carefully and make sure your class names are exactly the same as the configuration in VOCcode/VOCinit.m. And make sure ./imdb/cache/ folder clean before your training process. Good luck!

[Astrosun]

hello, have you solved this problem? I have the same problems when running experiments/script_faster_rcnn_VOC2007_ZF.m.

Thanks~

[lixiang-ucas]

you should change the class labels in VOCinit.m, make sure it match the labels in your Annotation .xml file.