# Support

**URL:** https://community.ultralytics.com/c/support/5.md

[Latest](https://community.ultralytics.com/latest.md) · [Categories](https://community.ultralytics.com/categories.md) · [Tags](https://community.ultralytics.com/tags.md)

---

## [Advice on asking for Support](https://community.ultralytics.com/t/advice-on-asking-for-support/126)

<div class="topic-metadata">

**Author:** [@BurhanQ](https://community.ultralytics.com/u/BurhanQ)\
**Replies:** 0\
**Last updated:** [July 23, 2024, 1:09pm UTC](https://community.ultralytics.com/t/advice-on-asking-for-support/126 "2024-07-23T13:09:58Z")

</div>

There’s a well known phenomena in providing support to others know as the XY-problem. Here’s a brief overview (quoted from the link, which you should absolutely visit and read) about what the XY-problem is: The XY prob…

---

## [About the Support category](https://community.ultralytics.com/t/about-the-support-category/11)

<div class="topic-metadata">

**Author:** [@UltraBot](https://community.ultralytics.com/u/UltraBot)\
**Replies:** 0\
**Last updated:** [June 12, 2024, 7:39pm UTC](https://community.ultralytics.com/t/about-the-support-category/11 "2024-06-12T19:39:36Z")

</div>

Lost, stuck, or confused? This is the place to go for asking for support from others in the community. Please keep in mind You are not here to have someone solve your problem for you, you are here to understand how t…

---

## [When using Platform deployment, intermittently, returned predictions contain false positives](https://community.ultralytics.com/t/when-using-platform-deployment-intermittently-returned-predictions-contain-false-positives/2241)

<div class="topic-metadata">

**Author:** [@stevem](https://community.ultralytics.com/u/stevem)\
**Replies:** 3\
**Last updated:** [September 27, 2026, 1:09am UTC](https://community.ultralytics.com/t/when-using-platform-deployment-intermittently-returned-predictions-contain-false-positives/2241 "2026-09-27T01:09:44Z")

</div>

Hi, I am using the Platform Deployment of a model that I have created. (Model is custom trained based on Yolo26s-seg 8.4.163) Intermittently, I have found that the Endpoint returns a false positive prediction. When I…

---

## [YOLO11x 推理时偶发背景高置信度误检，bbox 远大于真实目标且多发于右下角](https://community.ultralytics.com/t/yolo11x-bbox/2233)

<div class="topic-metadata">

**Author:** [@wzz\_come](https://community.ultralytics.com/u/wzz_come)\
**Replies:** 5\
**Last updated:** [September 25, 2026, 1:01am UTC](https://community.ultralytics.com/t/yolo11x-bbox/2233 "2026-09-25T01:01:16Z")

</div>

大家好， 我使用YOLO11x时遇到一个问题：使用模型推理时发现部分标签偶尔会将背景召回，且置信度大于0.99。 1、我已经检查训练集，并没有误标 2、之前是不存在这个问题的，是最近大概8月开始发现 3、并不是全部标签都这样，只有部分标签；并不是总是出现此类误检，是偶尔 4、误检位置大多数发生在图片右下角。有时误检是矩形，且bbox的大小是对应标签真实大小的好几倍；有时是一条线，即y值相等。 请不吝赐教，不胜感激。

---

## [Dataset processing stuck at 95%](https://community.ultralytics.com/t/dataset-processing-stuck-at-95/2225)

<div class="topic-metadata">

**Author:** [@Arona\_Anderson](https://community.ultralytics.com/u/Arona_Anderson)\
**Replies:** 5\
**Last updated:** [September 20, 2026, 1:24pm UTC](https://community.ultralytics.com/t/dataset-processing-stuck-at-95/2225 "2026-09-20T13:24:19Z")

</div>

My Dataset is stuck, it is at 95% processing. This started when trying to add more images to my existing dataset. I have refreshed the page, logged out and back in. I have event ried making a new dataset and uploading …

---

## [Using a self-trained model is unable to perform intelligent annotation](https://community.ultralytics.com/t/using-a-self-trained-model-is-unable-to-perform-intelligent-annotation/2204)

<div class="topic-metadata">

**Author:** [@jinwei\_li](https://community.ultralytics.com/u/jinwei_li)\
**Replies:** 2\
**Last updated:** [September 4, 2026, 9:16am UTC](https://community.ultralytics.com/t/using-a-self-trained-model-is-unable-to-perform-intelligent-annotation/2204 "2026-09-04T09:16:08Z")

</div>

I created a dataset of 200 images through the ultralytics platform, which contained 6 categories. Then I trained a model named best.pt. Subsequently, I wanted to use the best.pt model for smart annotation, so I added ano…

---

## [Export NDJSON doens't keep original filenames](https://community.ultralytics.com/t/export-ndjson-doenst-keep-original-filenames/2205)

<div class="topic-metadata">

**Author:** [@puccj](https://community.ultralytics.com/u/puccj)\
**Replies:** 2\
**Last updated:** [September 4, 2026, 9:05am UTC](https://community.ultralytics.com/t/export-ndjson-doenst-keep-original-filenames/2205 "2026-09-04T09:05:57Z")

</div>

Hello, I am using ultralytics platform to edit annotations in a dataset. I can download the annotation via the button on the top-right, which exports a .ndjson file. The file contains images’ names (“file”=…) and their …

---

## [How do YOLO chose the best epoch o save best.pt?](https://community.ultralytics.com/t/how-do-yolo-chose-the-best-epoch-o-save-best-pt/2179)

<div class="topic-metadata">

**Author:** [@Luciano\_Carvalheira](https://community.ultralytics.com/u/Luciano_Carvalheira)\
**Replies:** 7\
**Last updated:** [August 22, 2026, 1:27pm UTC](https://community.ultralytics.com/t/how-do-yolo-chose-the-best-epoch-o-save-best-pt/2179 "2026-08-22T13:27:51Z")

</div>

I am working with YOLO26.pt to segment images. I would like to know how YOLO choses the best epoch to save the trained model best.pt. I looked for some information, seems it choses the best model based on the metric mAp…

---

## [Replacing C3k2 with RepViT in YOLO11 While Reusing Pretrained Weights](https://community.ultralytics.com/t/replacing-c3k2-with-repvit-in-yolo11-while-reusing-pretrained-weights/2166)

<div class="topic-metadata">

**Author:** [@Hieu\_Nguyen\_Duc](https://community.ultralytics.com/u/Hieu_Nguyen_Duc)\
**Replies:** 1\
**Last updated:** [August 13, 2026, 6:15pm UTC](https://community.ultralytics.com/t/replacing-c3k2-with-repvit-in-yolo11-while-reusing-pretrained-weights/2166 "2026-08-13T18:15:21Z")

</div>

I am exploring waste detection and I want to replace the C3k2 blocks in the YOLO11 backbone with RepViT modules, while keeping the original YOLO11 neck and detection head. My main goal is to reuse the pretrained weights…

---

## [Training a Pose Model Using the Ultralytics GUI/Platform](https://community.ultralytics.com/t/training-a-pose-model-using-the-ultralytics-gui-platform/2154)

<div class="topic-metadata">

**Author:** [@mvyletel](https://community.ultralytics.com/u/mvyletel)\
**Replies:** 2\
**Last updated:** [August 8, 2026, 8:16am UTC](https://community.ultralytics.com/t/training-a-pose-model-using-the-ultralytics-gui-platform/2154 "2026-08-08T08:16:58Z")

</div>

Hello all, I’m trying to create a pose model using the ultralytics GUI/platform. I have a little over 50 images. I created just 1 class, “person”, which each point set is assigned to. When I attempt to train the model i…

---

## [YOLO11 or YOLO26 for Jetson Orin NX 16GB with a custom dataset](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145)

<div class="topic-metadata">

**Author:** [@Ahmad\_Khan](https://community.ultralytics.com/u/Ahmad_Khan)\
**Replies:** 5\
**Last updated:** [August 2, 2026, 12:58am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145 "2026-08-02T00:58:11Z")

</div>

Hello everyone, I’m using a Jetson Orin NX 16GB with a custom dataset, deployed with DeepStream, TensorRT, and INT8. Which model do you recommend, YOLO11 or YOLO26, and which size (l or x)? Thanks!

---

## [False detections](https://community.ultralytics.com/t/false-detections/2133)

<div class="topic-metadata">

**Author:** [@BilalAsifB](https://community.ultralytics.com/u/BilalAsifB)\
**Replies:** 1\
**Last updated:** [July 22, 2026, 7:07pm UTC](https://community.ultralytics.com/t/false-detections/2133 "2026-07-22T19:07:36Z")

</div>

I’m working on training the YOLO26m model to detect weapons, the model is very good at detecting weapons but it also detects dark spots or different objects as guns. My dataset has approx. 10000 images, they are all wel…

---

## [Export error using the website](https://community.ultralytics.com/t/export-error-using-the-website/2122)

<div class="topic-metadata">

**Author:** [@ErnestLB](https://community.ultralytics.com/u/ErnestLB)\
**Replies:** 5\
**Last updated:** [July 19, 2026, 12:56am UTC](https://community.ultralytics.com/t/export-error-using-the-website/2122 "2026-07-19T00:56:44Z")

</div>

Hi, Using the website(https://platform.ultralytics.com) I just created my first project, upload the dataset, classified, trainned, and when completed, I try to download the .tflite file by using the correspondent “expo…

---

## [Class name mispelled in the LVIS dataset](https://community.ultralytics.com/t/class-name-mispelled-in-the-lvis-dataset/2121)

<div class="topic-metadata">

**Author:** [@Guillaume\_O](https://community.ultralytics.com/u/Guillaume_O)\
**Replies:** 2\
**Last updated:** [July 17, 2026, 5:21pm UTC](https://community.ultralytics.com/t/class-name-mispelled-in-the-lvis-dataset/2121 "2026-07-17T17:21:31Z")

</div>

Hello, I am using the LVIS class names for evaluation of text-image similarity and I observed a class name mispelled on this page:LVIS Detection Dataset | Ultralytics . The class 666 is spelled “manager/through” and sho…

---

## [I subscribed ultralytics pro plan but still free user](https://community.ultralytics.com/t/i-subscribed-ultralytics-pro-plan-but-still-free-user/2119)

<div class="topic-metadata">

**Author:** [@daniel\_private20](https://community.ultralytics.com/u/daniel_private20)\
**Replies:** 1\
**Last updated:** [July 16, 2026, 10:33am UTC](https://community.ultralytics.com/t/i-subscribed-ultralytics-pro-plan-but-still-free-user/2119 "2026-07-16T10:33:10Z")

</div>

To use ultralyrics more efficient, I payed $29 for subscription of ultralytics pro plan. But still showing as I’m free plan user. What I did 1.refreshed n sign out n sign in Checked that I have invoice n receipt o…

---

## [I want precdict threading](https://community.ultralytics.com/t/i-want-precdict-threading/2100)

<div class="topic-metadata">

**Author:** [@yuns](https://community.ultralytics.com/u/yuns)\
**Replies:** 2\
**Last updated:** [July 6, 2026, 10:48pm UTC](https://community.ultralytics.com/t/i-want-precdict-threading/2100 "2026-07-06T22:48:38Z")

</div>

I want to perform inference on an array of 500 images using threads. Ask AI said to use it thie way but, this code Thread collision error -\> not use predict Thread error from threading import Thread from ultralytics …

---

## [Do you ever alter the form of the input image during the image inference process?](https://community.ultralytics.com/t/do-you-ever-alter-the-form-of-the-input-image-during-the-image-inference-process/2089)

<div class="topic-metadata">

**Author:** [@yuns](https://community.ultralytics.com/u/yuns)\
**Replies:** 3\
**Last updated:** [July 1, 2026, 1:59pm UTC](https://community.ultralytics.com/t/do-you-ever-alter-the-form-of-the-input-image-during-the-image-inference-process/2089 "2026-07-01T13:59:34Z")

</div>

The color of this image was corrupted, so it was flagged by the detection system.

---

## [Removing NNPACK 'complaint'](https://community.ultralytics.com/t/removing-nnpack-complaint/2086)

<div class="topic-metadata">

**Author:** [@hbarnard](https://community.ultralytics.com/u/hbarnard)\
**Replies:** 1\
**Last updated:** [June 29, 2026, 1:24am UTC](https://community.ultralytics.com/t/removing-nnpack-complaint/2086 "2026-06-29T01:24:58Z")

</div>

I’m running a simple prototype on a CPU only system. I noticed that you’ve enabled suppression in Docker via torch.backends.nnpack.enabled = False and I’d like to do the same in yolo CLI or Python or both? It’s a nuisa…

---

## [Best approach to count stacked cardboard boxes using CCTV (2D RGB only)](https://community.ultralytics.com/t/best-approach-to-count-stacked-cardboard-boxes-using-cctv-2d-rgb-only/1581)

<div class="topic-metadata">

**Author:** [@Muhammad\_Fhadli](https://community.ultralytics.com/u/Muhammad_Fhadli)\
**Replies:** 4\
**Last updated:** [June 16, 2026, 1:32am UTC](https://community.ultralytics.com/t/best-approach-to-count-stacked-cardboard-boxes-using-cctv-2d-rgb-only/1581 "2026-06-16T01:32:03Z")

</div>

Hi everyone :waving\_hand: I’m working on a real-world counting problem and would love to get some advice or ideas from the community. I need to count the number of cardboard boxes in a warehouse — similar to this examp…

---

## [Export yolov11s at a size different from default one](https://community.ultralytics.com/t/export-yolov11s-at-a-size-different-from-default-one/1974)

<div class="topic-metadata">

**Author:** [@cridemichel](https://community.ultralytics.com/u/cridemichel)\
**Replies:** 9\
**Last updated:** [May 15, 2026, 7:11pm UTC](https://community.ultralytics.com/t/export-yolov11s-at-a-size-different-from-default-one/1974 "2026-05-15T19:11:57Z")

</div>

Dear All, I am using Hailo-8L with frigate in home assistant on a raspberry pi 5 for videosurveillance. I already exported yolov11s model at a resolution of 480x480 without any fine-tuning and I compiled it for hailo-…

---

## [Detecting court keypoints from a pickleball video](https://community.ultralytics.com/t/detecting-court-keypoints-from-a-pickleball-video/1703)

<div class="topic-metadata">

**Author:** [@kunal](https://community.ultralytics.com/u/kunal)\
**Replies:** 10\
**Last updated:** [May 12, 2026, 12:34pm UTC](https://community.ultralytics.com/t/detecting-court-keypoints-from-a-pickleball-video/1703 "2026-05-12T12:34:50Z")

</div>

I am trying to train a Yolov8 model to detect the keypoints of a pickleball court. I have annotated a dataset of 2000 images (1920 x 1080) which I have split into 1400 train - 400 valid - 200 test. In addition I applied…

---

## [Exporting the RKNN model after training on the official platform failed.](https://community.ultralytics.com/t/exporting-the-rknn-model-after-training-on-the-official-platform-failed/1950)

<div class="topic-metadata">

**Author:** [@jackyuan](https://community.ultralytics.com/u/jackyuan)\
**Replies:** 2\
**Last updated:** [May 3, 2026, 2:58pm UTC](https://community.ultralytics.com/t/exporting-the-rknn-model-after-training-on-the-official-platform-failed/1950 "2026-05-03T14:58:19Z")

</div>

---

## [Conversion du type d'annotation des données](https://community.ultralytics.com/t/conversion-du-type-dannotation-des-donnees/1925)

<div class="topic-metadata">

**Author:** [@Christian\_SAWADOGO](https://community.ultralytics.com/u/Christian_SAWADOGO)\
**Replies:** 6\
**Last updated:** [April 9, 2026, 5:38pm UTC](https://community.ultralytics.com/t/conversion-du-type-dannotation-des-donnees/1925 "2026-04-09T17:38:46Z")

</div>

Good morning! I hope you’re doing well! When annotating my data I used two combined types, notably annotation in the form of polygons and in the form of bbox. Now after I realized that it was not possible to have both t…

---

## [Using photos for training a model. How to choose the right resolution for taking photos?](https://community.ultralytics.com/t/using-photos-for-training-a-model-how-to-choose-the-right-resolution-for-taking-photos/1918)

<div class="topic-metadata">

**Author:** [@fziegler76](https://community.ultralytics.com/u/fziegler76)\
**Replies:** 3\
**Last updated:** [April 7, 2026, 6:56pm UTC](https://community.ultralytics.com/t/using-photos-for-training-a-model-how-to-choose-the-right-resolution-for-taking-photos/1918 "2026-04-07T18:56:04Z")

</div>

I am a beginner and am just about to take the first step in training a yolo model. I need to detect defects on wooden boards (such as knots, cracks, etc.). The boards are 1300x100 mm in size. I will use a single camera w…

---

## [Ultralytics platform](https://community.ultralytics.com/t/ultralytics-platform/1911)

<div class="topic-metadata">

**Author:** [@Miguel\_Wisintainer](https://community.ultralytics.com/u/Miguel_Wisintainer)\
**Replies:** 6\
**Last updated:** [April 5, 2026, 1:58am UTC](https://community.ultralytics.com/t/ultralytics-platform/1911 "2026-04-05T01:58:27Z")

</div>

Hi, I am using ultralytics platform to train my monkey database class, using the YOLO8N–CLS, all going well, i can test the ultralytics predict to certify the correct train and after converted to my SG2002 hardware, a…

---

## [Daphnia tracking system using YOLO](https://community.ultralytics.com/t/daphnia-tracking-system-using-yolo/1906)

<div class="topic-metadata">

**Author:** [@LauraO101](https://community.ultralytics.com/u/LauraO101)\
**Replies:** 6\
**Last updated:** [March 31, 2026, 1:38am UTC](https://community.ultralytics.com/t/daphnia-tracking-system-using-yolo/1906 "2026-03-31T01:38:21Z")

</div>

Hi there, I’m a highschool student trying to create a tracking software with YOLO AI for daphnia movement. Currently I’m testing my program with a datapool of 60 pictures from a 1 min video. (1 picture per 1 second) Howe…

---

## [YOLO26n-Pose in Xcode](https://community.ultralytics.com/t/yolo26n-pose-in-xcode/1903)

<div class="topic-metadata">

**Author:** [@Spencer\_A](https://community.ultralytics.com/u/Spencer_A)\
**Replies:** 3\
**Last updated:** [March 29, 2026, 1:38pm UTC](https://community.ultralytics.com/t/yolo26n-pose-in-xcode/1903 "2026-03-29T13:38:12Z")

</div>

Hello, I am trying to run a yolo26n-pose model on my iphone and I am using xcode to do this. I have read the yolo on ios documentation on github, and have followed the instructions regarding converting the model to coreM…

---

## [YOLO is not reading correctly the training data](https://community.ultralytics.com/t/yolo-is-not-reading-correctly-the-training-data/1899)

<div class="topic-metadata">

**Author:** [@Luciano\_Carvalheira](https://community.ultralytics.com/u/Luciano_Carvalheira)\
**Replies:** 9\
**Last updated:** [March 27, 2026, 1:46pm UTC](https://community.ultralytics.com/t/yolo-is-not-reading-correctly-the-training-data/1899 "2026-03-27T13:46:17Z")

</div>

Hello everybody, I am training a YOLO algoriths (yolo26n-seg.pt) to detec blastocysts, an early embryo development stage, in photos. However, I am facing some trouble on the training process. I labeled the images in R…

---

## [System Freeze When Performing Heavy Yolo Inferencing](https://community.ultralytics.com/t/system-freeze-when-performing-heavy-yolo-inferencing/1882)

<div class="topic-metadata">

**Author:** [@Christian\_G\_A](https://community.ultralytics.com/u/Christian_G_A)\
**Replies:** 7\
**Last updated:** [March 25, 2026, 4:53pm UTC](https://community.ultralytics.com/t/system-freeze-when-performing-heavy-yolo-inferencing/1882 "2026-03-25T16:53:43Z")

</div>

Hello, I have been using YOLO inferencing for about a year to analyze 24 camera feeds. I have one dedicated computer for this purpose, a new ASUS desktop that has powerful specs. The inference runs about every 1 second …

---

## [Can i train model with Rectangle ratio images?](https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874)

<div class="topic-metadata">

**Author:** [@iscream](https://community.ultralytics.com/u/iscream)\
**Replies:** 3\
**Last updated:** [March 18, 2026, 5:01pm UTC](https://community.ultralytics.com/t/can-i-train-model-with-rectangle-ratio-images/1874 "2026-03-18T17:01:03Z")

</div>

Hi im trying to find USB camera and Thrmal camera module for my Xavier NX developer Kit. I realized that those modules usually support 4:3 ratio images. I’m worring about resizing image which could makes my model dumb.…

[Next page](https://community.ultralytics.com/c/support/5.md?page=1)
