Closed BeingGod closed 3 years ago
image_id
and id
is only or not? IM_0000.jpg
is 0 in train.json
and the id of IM_0001.jpg
is also 0 in val.json
.1. And I also want to know whether the `image_id` and `id` is **only** or not? 2. Can share id in different json files? such as the id of `IM_0000.jpg` is **0** in `train.json` and the id of `IM_0001.jpg` is **also 0** in `val.json`.
@BeingGod did you find out anything? I'm facing the same issue and I would like to know the answer to those questions you ask. Thanks!
Same here
ME TOO.
maybe you need to modify the mmdet/datasets/xxx.py
and mmdet/core/evaluation/class_names.py
for matching your own dataset👍
ME TOO.
have you solved it?
Yes,you have to know the detail!
发送自 Windows 10 版邮件应用
发件人: tingfengwanxiao 发送时间: 2020年10月26日 20:12 收件人: open-mmlab/mmdetection 抄送: Caesar; Comment 主题: Re: [open-mmlab/mmdetection] ValueError: need at least one array toconcatenate (#2928)
ME TOO. have you solved it? — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
he detail!
then,how do you solve the problem,I can check whether I meet the same problem.
he detail!
then,how do you solve the problem,I can check whether I meet the same problem.
I get same error message. I found a solution on issues and fixed it by change image_id from type string to int and value of key 'segmentation' from list to list of list like this
"segmentation": [1,2] -> "segmentation": [[1,2]]
All modification is in my coco json annotation!
I meet a ERROR when I trained my custom dataset whose format is COCO. I browsed some issues but them couldn't help me solve this problem.
My config file
The content of
test.json
I make sure the type of
image_id
andid
isint
Besides, I can train coco2017 normally.