fruit数据集 运行eval.py 报错没有gt_bbox
Created by: qjing666
如题,用faster_rcnn模型训练fruit数据集,并有模型保存到 output/faster_rcnn_r50_fruit/ 路径下,在验证模型在测试集的效果时 运行 " python -u tools/eval.py -c configs/faster_rcnn_r50_fruit.yml -o weights=output/faster_rcnn_r50_fruit/" 报错如下:
Traceback (most recent call last): File "tools/eval.py", line 190, in main() File "tools/eval.py", line 173, in main dataset=dataset) File "/home/jingqinghe/PaddleDetection/ppdet/utils/eval_utils.py", line 226, in eval_results map_type=map_type) File "/home/jingqinghe/PaddleDetection/ppdet/utils/voc_eval.py", line 73, in bbox_eval gt_boxes = t['gt_bbox'][0] KeyError: 'gt_bbox'