# Inference API Bounding Boxes Offset

**URL:** <https://discuss.roboflow.com/t/inference-api-bounding-boxes-offset/2923>\
**Category:** 🤝  Community Help\
**Created:** [August 13, 2023, 7:05am UTC](https://discuss.roboflow.com/t/inference-api-bounding-boxes-offset/2923 "2023-08-13T07:05:47Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![vijay](https://avatars.discourse-cdn.com/v4/letter/v/4bbf92/32.png) [@vijay](https://discuss.roboflow.com/u/vijay)\
**Post date:** [August 13, 2023, 7:05am UTC](https://discuss.roboflow.com/t/inference-api-bounding-boxes-offset/2923/1 "2023-08-13T07:05:47Z")

</div>

Hi, I am facing an issue with the Roboflow. After training the model, i have downloaded the code and predicted on new image in Jupyter notebook using Opencv, the bounding box is showing at an offset. The coordinates it is giving are at a little offset. For every image it is giving an offset.

I have a long image, i cropped the image into equal parts. I am annotating on the equally cropped images and trained the model. When i am giving the same cropped image it is showing the bounding boxes at wrong coordinates.

I am inferring images with hosted API, project name and version. One thing I am training and predicting on the image that have same resolution but still facing an offset.

I am uploading 2 images that are when i am annotating in Roboflow and other one is when it predicted after training.

 ![all1](https://canada1.discourse-cdn.com/flex029/uploads/roboflow1/original/2X/e/e222e0e9ca388b7090daf51079727364f6e37103.jpeg)

 ![all1_all](https://canada1.discourse-cdn.com/flex029/uploads/roboflow1/original/2X/3/374e7ad7f657ed59c0e817b916a3826bf51e32ba.jpeg)

---

<div class="post-metadata">

**Author:** ![leo](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/leo/32/2228_2.png) [@leo](https://discuss.roboflow.com/u/leo)\
**Post date:** [August 13, 2023, 7:12am UTC](https://discuss.roboflow.com/t/inference-api-bounding-boxes-offset/2923/2 "2023-08-13T07:12:28Z")

</div>

Hi @vijay

Sorry to hear you’re having issues. Roboflow’s inference server provides outputs for `x` and `y` as the center point of the detected object. See more about this on [the relevant section from the docs](https://docs.roboflow.com/deploy/hosted-api/object-detection#response-object-format). Could that be the source of your issues?

If you’re looking for a easy way to display your inferred predictions, I suggest using [supervision’s](https://roboflow.github.io/supervision) [`from_roboflow()`](https://roboflow.github.io/supervision/detection/core/#supervision.detection.core.Detections.from_roboflow) function and the [`plot_image()`](https://roboflow.github.io/supervision/utils/notebook/#plot_image) function.

---

<div class="post-metadata">

**Author:** ![peter\_roboflow](https://yyz1.discourse-cdn.com/flex029/user_avatar/discuss.roboflow.com/peter_roboflow/32/2609_2.png) [@peter\_roboflow](https://discuss.roboflow.com/u/peter_roboflow)\
**Post date:** [August 13, 2023, 8:11am UTC](https://discuss.roboflow.com/t/inference-api-bounding-boxes-offset/2923/3 "2023-08-13T08:11:50Z")

</div>

@vijay did you use the static-crop augmentation? try feeding the whole image to the model, not the cropped version. it should do the cropping as a preprocessing step