# issue in training a computer vision

**URL:** <https://support.prodi.gy/t/issue-in-training-a-computer-vision/3301>\
**Category:** Uncategorized\
**Tags:** usage, image\
**Created:** [August 17, 2020, 8:14am UTC](https://support.prodi.gy/t/issue-in-training-a-computer-vision/3301 "2020-08-17T08:14:14Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![shubham\_jain](https://avatars.discourse-cdn.com/v4/letter/s/e79b87/32.png) [@shubham\_jain](https://support.prodi.gy/u/shubham_jain)\
**Post date:** [August 17, 2020, 8:14am UTC](https://support.prodi.gy/t/issue-in-training-a-computer-vision/3301/1 "2020-08-17T08:14:14Z")

</div>

how to train a annotate dataset of image, what is the synatax?

---

<div class="post-metadata">

**Author:** ![ines](https://sea2.discourse-cdn.com/flex020/user_avatar/support.prodi.gy/ines/32/3_2.png) [@ines](https://support.prodi.gy/u/ines)\
**Post date:** [August 18, 2020, 9:03am UTC](https://support.prodi.gy/t/issue-in-training-a-computer-vision/3301/2 "2020-08-18T09:03:19Z")

</div>

Hi! Prodigy itself doesn't ship with a built-in recipe for training a computer vision model. There are many different implementations and frameworks, so you'd have to pick the type of model you want to use. How the training works in detail depends on the framework (PyTorch, TensorFlow etc.) and model architecture/implementation.

You can see an example of the data format produced by Prodigy's `image_manual` recipe here: [https://prodi.gy/docs/api-interfaces#image\_manual](https://prodi.gy/docs/api-interfaces#image_manual) This should make it easy to update the model with what it needs: for each annotated bounding box, you'll have the coordinates, width, height and label. You can use the `db-out` command to export your dataset to JSON, and then use the data to train your model.