Created by: CrazyRockWZJ

我已经将Config cascade_rcnn_r50_fpn_1x.yml中相应的参数设置为：

metric: VOC

FasterRCNNTrainFeed: batch_size: 1 dataset: dataset_dir: dataset/voc annotation: VOCdevkit/VOC_all/ImageSets/Main/train.txt image_dir: VOCdevkit/VOC_all/JPEGImages batch_transforms:

• !PadBatch pad_to_stride: 32 drop_last: false num_workers: 2

FasterRCNNEvalFeed: batch_size: 1 dataset: dataset_dir: dataset/voc annotation: VOCdevkit/VOC_all/ImageSets/Main/val.txt image_dir: VOCdevkit/VOC_all/JPEGImages batch_transforms:

• !PadBatch pad_to_stride: 32

FasterRCNNTestFeed: batch_size: 1 dataset: annotation: VOCdevkit/VOC_all/ImageSets/Main/test.txt batch_transforms: 可是在使用脚本python tools/train.py -c configs/cascade_rcnn_r50_fpn_1x.yml训练时报错显示： consumer failed with error: failed to map consumer[%s], error: [Errno 2] No such file or directory: 'dataset/voc/VOCdevkit/VOC_all/JPEGImages/15524713780796.json' 请问，使用自己的VOC数据训练CascadeRCNN我还需要修改哪些内容。