[X] 1. I have searched related issues but cannot get the expected help.
[ ] 2. The bug has not been fixed in the latest version.
[ ] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
Describe the bug
我用自己的数据集微调之后,想评测一下模型性能,按照官方文档,选了refcoco的(GPUS=8 sh evalulate.sh pretrained/InternVL2-2B refcoco --dynamic)
就报错FileNotFoundError: [Errno 2] No such file or directory: 'data/refcoco/refcoco_val.jsonl',这个文件哪里有呢?
Reproduction
我用自己的数据集使用intervl2-2B的模型进行了微调,这个数据集是按照如下格式描述的
{
"id": 0,
"image": "images/5.png",
"conversations": [
{
"from": "human",
"value": "\nPlease provide the bounding box coordinate of the region this sentence describes: XXX"
},
{
"from": "gpt",
"value": "XXX[[253, 231, 733, 787]]"
}
}
模型完成微调之后,可以正常对话,但是推理的时候输出的坐标不准确。
在对模型评估的时候,因为我做的目标检测,找了refcoco的评测,然后就报错了。
另外还有两个问题请教一下:
1.我看了官方文档里refcoco那些指标,这些数值是什么含义呢,这个refcoco指标的评测可以作为目标检测的评估指标吗?
Checklist
Describe the bug
我用自己的数据集微调之后,想评测一下模型性能,按照官方文档,选了refcoco的(GPUS=8 sh evalulate.sh pretrained/InternVL2-2B refcoco --dynamic) 就报错FileNotFoundError: [Errno 2] No such file or directory: 'data/refcoco/refcoco_val.jsonl',这个文件哪里有呢?
Reproduction
我用自己的数据集使用intervl2-2B的模型进行了微调,这个数据集是按照如下格式描述的 { "id": 0, "image": "images/5.png", "conversations": [ { "from": "human", "value": "\nPlease provide the bounding box coordinate of the region this sentence describes: XXX"
},
{
"from": "gpt",
"value": "XXX[[253, 231, 733, 787]] "
}
}
模型完成微调之后,可以正常对话,但是推理的时候输出的坐标不准确。
在对模型评估的时候,因为我做的目标检测,找了refcoco的评测,然后就报错了。
另外还有两个问题请教一下:
1.我看了官方文档里refcoco那些指标,这些数值是什么含义呢,这个refcoco指标的评测可以作为目标检测的评估指标吗?
2.模型在推理的时候输出的坐标位置不准确,这个怎么提升呢,是要上到26B以上的模型吗,我看26B以下的模型视觉部分都是一样的,还是有其他提升的点呢?
Environment
Error traceback
No response