Giter VIP home page Giter VIP logo

Comments (21)

jingeyijie avatar jingeyijie commented on July 24, 2024 2

研究生毕业论文

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

数学公式是啥啊?

是这种问题嘛 PaddlePaddle/PaddleDetection#8430

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

例如:小学生的试卷。 我想通过 RT—DETR模型训练,然后可以检测出照片中的数学公式,如 4+5=9
我现在是设置了
num_classes: 1
新增了自己的数学公式类别:
{
"supercategory": "formula",
"id": 1,
"name": "mathematical formula"
}
自己的数据集,按照格式要求转换了。

训练命令:python -m paddle.distributed.launch --gpus 0,1,2,3 tools/train.py -c configs/rtdetr/rtdetr_r50vd_6x_coco.yml --fleet --eval

但是训练结束过程中AP基本都是0,然后测试的时候检测的结果不理想。

  1. 有没有类似成功的案例,关于数学公式检测的。
  2. 如果同样的数据集继续训练收敛,是不是 python -m paddle.distributed.launch --gpus 0,1,2,3 tools/train.py -c configs/rtdetr/rtdetr_r50vd_6x_coco.yml --fleet --eval 直接用即可。

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

理论上是的 之前没有做过数学公式检测能给个图看看嘛,得确定下是( 数据内容 or 只是1类的)训练不出来的问题

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

aec_0

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

DONE (t=0.01s).
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
一直都是0

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

改成两类试一下,, 有试过其他检测器嘛

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

没有尝试其他检测器。这边要求要用RT-DETR模型的。

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

那就先确定下是不是做1类检测效果的不行

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

没有尝试其他检测器。这边要求要用RT-DETR模型的。

@jingeyijie

方便透露一下什么单位嘛😳

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

检测一下数据格式 box format等

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

我设置了两个类别,AP还全是0

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
[08/21 00:00:15] ppdet.engine INFO: Total sample number: 1000, average FPS: 21.3426494658262
[08/21 00:00:15] ppdet.engine INFO: Best test bbox ap is 0.000.

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

坐标是xywh嘛 xy是box的左上角

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

坐标是 xywh的。 xy是box的左上角

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

理论上是不是这类数学公式是可以训练出来的? 只需要训练数学公式一个类型的。
image

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

这个感觉问题不大吧 但是之前确实没有跑过类似的数据

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

我昨天检查了 box 坐标都OK,还尝试了其他的预模型。但是训练过程中还是AP都是0,我理解这个就是有问题的吧。

Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = -1.000
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.000
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.000

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

这里我需要修改哪些参数。我按照文档要求改了:
coco_detection.yml 指定自己数据集路径,num_classes 改为了1
然后就没改其他的内容。

from rt-detr.

lyuwenyu avatar lyuwenyu commented on July 24, 2024

其他是不需要改的了

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

要不我把我的数据集上传,帮我看看哪里出了问题?

from rt-detr.

jingeyijie avatar jingeyijie commented on July 24, 2024

我换了 fcos 模型训练是成功的。 RT-DETR 训练不行的。

from rt-detr.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.