# New Release: Ultralytics v8.3.250

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-3-250/1736>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [January 9, 2026, 1:16pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-250/1736 "2026-01-09T13:16:51Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![glenn-jocher](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/glenn-jocher/32/83_2.png) [@glenn-jocher](https://community.ultralytics.com/u/glenn-jocher)\
**Post date:** [January 9, 2026, 1:16pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-3-250/1736/1 "2026-01-09T13:16:51Z")

</div>

# Ultralytics v8.3.250 is out 🚀🚦

**Quick overview:** v8.3.250 brings **out-of-the-box support for the TT100K traffic sign dataset** (auto-download + auto-convert to YOLO labels), plus smoother dataset URI handling, cleaner run directory behavior, and a handful of quality/build/docs fixes 🛠📚

* * *

## 🚦 New Features

### TT100K dataset integration (221 classes)

Big thanks to [@PrashantDixit0](https://github.com/PrashantDixit0) for adding first-class TT100K support in PR [#22892](https://github.com/ultralytics/ultralytics/pull/22892) 🎉

**What you get:**

- New dataset config at `ultralytics/cfg/datasets/TT100K.yaml` with full metadata
- **Auto download + conversion pipeline** that fetches TT100K and converts annotations into **YOLO-format labels** automatically
- New docs page integrated into navigation via the [TT100K dataset documentation](https://docs.ultralytics.com/datasets/detect/tt100k/) 🚦

**Try it:**

```bash
yolo detect train data=TT100K.yaml model=yolo11n.pt

```

* * *

## 🌐 Improvements

### Dataset URI support + automatic NDJSON → YOLO conversion

PR [#23146](https://github.com/ultralytics/ultralytics/pull/23146) by [@glenn-jocher](https://github.com/glenn-jocher) improves training workflows when using `ul://.../datasets/...` sources:

- `ul://` dataset sources are now resolved locally first
- **NDJSON datasets are automatically converted to YOLO format**
- Smarter `--project` handling for nested names like `user/project`, keeping runs organized under the expected runs directory
- Updates to the platform webhook base URL used by the platform callback resolver

* * *

## 📚 Documentation Updates

### Better Kaggle install + troubleshooting guidance

PR [#22970](https://github.com/ultralytics/ultralytics/pull/22970) by [@PrashantDixit0](https://github.com/PrashantDixit0) adds a clearer Kaggle **Installation** section (internet toggle, install commands, conflict fixes) to reduce setup friction ⚡

* * *

## 🧩 Bug Fixes

### ConfusionMatrix default type mismatch fix

PR [#23138](https://github.com/ultralytics/ultralytics/pull/23138) by [@raimbekovm](https://github.com/raimbekovm) fixes `ConfusionMatrix(names=...)` default from `[]` to `{}` to match the annotated type and avoid mutable-default pitfalls ✅

* * *

## 🛠 Build / Maintenance

### ONNXRuntime C++ example build improvement

First contribution from [@omar-A-hassan](https://github.com/omar-A-hassan) in PR [#23137](https://github.com/ultralytics/ultralytics/pull/23137) 🎉  
CMake now respects user-provided `ONNXRUNTIME_ROOT`, making custom install paths work as documented.

### Dependency update

PR [#23143](https://github.com/ultralytics/ultralytics/pull/23143) by [@dependabot[bot]](https://github.com/dependabot) bumps `urllib3` in the RT-DETR ONNXRuntime Python example requirements.

* * *

## ⬆ How to update

```bash
pip install -U ultralytics

```

* * *

## 🔗 Release links

You can review the full release notes in the [Ultralytics v8.3.250 GitHub release](https://github.com/ultralytics/ultralytics/releases/tag/v8.3.250) and browse changes in the [full changelog comparison](https://github.com/ultralytics/ultralytics/compare/v8.3.249...v8.3.250).

* * *

## 🙌 Feedback welcome

Give v8.3.250 a spin—especially **TT100K training** and `ul://` dataset flows—and reply here with results, issues, or suggestions. Your feedback helps the whole YOLO community and the Ultralytics team keep improving 🔧