# 2 bound boxes for same object

**URL:** <https://discuss.roboflow.com/t/2-bound-boxes-for-same-object/545>\
**Category:** 🤝  Community Help\
**Created:** [June 10, 2022, 6:24am UTC](https://discuss.roboflow.com/t/2-bound-boxes-for-same-object/545 "2022-06-10T06:24:50Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![mo\_t1](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mo_t1/32/382_2.png) [@mo\_t1](https://discuss.roboflow.com/u/mo_t1)\
**Post date:** [June 10, 2022, 6:24am UTC](https://discuss.roboflow.com/t/2-bound-boxes-for-same-object/545/1 "2022-06-10T06:24:50Z")

</div>

1- I have an object Detection , project, using roboflow , on google chrome,  
2- I made model in roboflow and trained it in Google Colab  
but the detection always has the problem like this image  
 ![image](https://canada1.discourse-cdn.com/flex029/uploads/roboflow1/original/1X/4e51942b0504a8f7b89292e8d604ec2b89d97340.jpeg)

why I don’t know give 2 round boxes each with different object name

---

<div class="post-metadata">

**Author:** ![Mohamed](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/mohamed/32/62_2.png) [@Mohamed](https://discuss.roboflow.com/u/Mohamed)\
**Post date:** [June 10, 2022, 5:22pm UTC](https://discuss.roboflow.com/t/2-bound-boxes-for-same-object/545/2 "2022-06-10T17:22:02Z")

</div>

Hi @mo_t1, it looks like your model has two classes it has trouble differentiating between.

I recommend [implementing Active Learning](https://help.roboflow.com/guides/implementing-active-learning) and taking more examples of the PKS and RPG classes, as well as this example image, and from there:

1. [upload them to Roboflow](https://help.roboflow.com/dataset-upload-roboflow-data-types)
2. [Annotate the images](https://help.roboflow.com/labeling-guide-object-detection)
3. Generate a new version of your dataset
4. Retrain your model
5. Retest your model on a similar image, and more images, and repeat the process to root out errors and raise the confidence level on all detections
