# I’m trying to make a tflite usuing edge impusle but it’s not working when i put the files in the cam

**URL:** <https://forums.openmv.io/t/i-m-trying-to-make-a-tflite-usuing-edge-impusle-but-it-s-not-working-when-i-put-the-files-in-the-cam/9679>\
**Category:** OpenMV Boards\
**Created:** [June 11, 2024, 5:56am UTC](https://forums.openmv.io/t/i-m-trying-to-make-a-tflite-usuing-edge-impusle-but-it-s-not-working-when-i-put-the-files-in-the-cam/9679 "2024-06-11T05:56:33Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![destinko497](https://avatars.discourse-cdn.com/v4/letter/d/7ba0ec/32.png) [@destinko497](https://forums.openmv.io/u/destinko497)\
**Post date:** [June 11, 2024, 5:56am UTC](https://forums.openmv.io/t/i-m-trying-to-make-a-tflite-usuing-edge-impusle-but-it-s-not-working-when-i-put-the-files-in-the-cam/9679/1 "2024-06-11T05:56:33Z")

</div>

I’m trying to make a a object detection software that finds goals on an and image that the camera takes and tells me where they are so i can track them. But i have a problem when i train the model on edge impulse with my images the model is too big (i think it says 110K flash size 250K Ram usage) so i could i make it smaller ive been trying for a long time but it seems that nothing helps. Or if size is not the issue the thing that happens is i put all the required files into the cam and run my code but it doesn’t detect anything even if i set min confidence to 0 while before with a different tflite it worked perfectly. I really appreciate any help i can get thank you.

---

<div class="post-metadata">

**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\
**Post date:** [June 11, 2024, 12:42pm UTC](https://forums.openmv.io/t/i-m-trying-to-make-a-tflite-usuing-edge-impusle-but-it-s-not-working-when-i-put-the-files-in-the-cam/9679/2 "2024-06-11T12:42:28Z")

</div>

What camera are you using? The RT1062 and H7 Plus have 32 MB of RAM onboard. There’s no artificial limit for your model size.
