search

WXinlong / SOLO

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.
Other
1.69k stars 307 forks source link

if 'caption' in anns[0]: IndexError: list index out of range #169

Open huangshouyou opened 3 years ago

huangshouyou commented 3 years ago

Thanks for your error report and we appreciate it a lot.

[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 18/18, 19.6 task/s, elapsed: 1s, ETA: 0s writing results to results_solo.pkl Starting evaluate segm Loading and preparing results... Traceback (most recent call last): File "tools/test_ins.py", line 257, in main() File "tools/test_ins.py", line 235, in main coco_eval(result_files, eval_types, dataset.coco) File "/home/atm/hsyou/SOLO/mmdet/core/evaluation/coco_utils.py", line 41, in coco_eval coco_dets = coco.loadRes(result_file) File "/home/atm/anaconda3/envs/solo/lib/python3.7/site-packages/pycocotools-2.0-py3.7-linux-x86_64.egg/pycocotools/coco.py", line 326, in loadRes if 'caption' in anns[0]: IndexError: list index out of range

zhuaiyi commented 3 years ago

I have met the same problem. Unsolved yet.

gernophil commented 3 years ago

Any solutions on this yet? Having the same error? Seems to be related to the bbox annotations, but I wasn't able to rule this error out yet.

tpfLZ commented 2 years ago

I have met the same problem.

onepiece010938 commented 2 years ago

same problem QQ

jiangxinhao2020 commented 2 years ago

Has anyone solved the problem?

songyangsun commented 2 years ago

if you use coco format, please check class. then you should confirm the path you train,i make a mistake on training path.

renxingaming commented 1 year ago

i have met the same problems. how can solve this problem? i have solved this problem today! if u meet the same problem, you can try to adjust training parameters to train the model again because the previous model cann't sgement.

jiubie12 commented 1 year ago

我遇到了同样的问题。如何解决这个问题？我今天解决了这个问题！如果遇到同样的问题，可以尝试调整训练参数来再次训练模型，因为之前的模型无法训练。

请问，怎样调整训练参数呢？

renxingaming commented 1 year ago

出现这个问题是因为测试集中某张图像没有目标被分割出。

------------------ 原始邮件 ------------------ 发件人: "WXinlong/SOLO" @.>; 发送时间: 2023年7月22日(星期六) 晚上11:05 @.>; @.**@.>; 主题: Re: [WXinlong/SOLO] if 'caption' in anns[0]: IndexError: list index out of range (#169)

我遇到了同样的问题。如何解决这个问题？我今天解决了这个问题！如果遇到同样的问题，可以尝试调整训练参数来再次训练模型，因为之前的模型无法训练。

请问，怎样调整训练参数呢？

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

yunhuiming commented 7 months ago

那如果测试集中某张图片的确没有目标怎么办