# New Release: Ultralytics v8.4.45

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-45/1952>\
**Category:** Discussion\
**Tags:** announcements, ultralytics-official, releases\
**Created:** [April 30, 2026, 1:35pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-45/1952 "2026-04-30T13:35:59Z")\
**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:** [April 30, 2026, 1:35pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-45/1952/1 "2026-04-30T13:35:59Z")

</div>

# 🚀 Ultralytics v8.4.45 Released

**Summary:** Ultralytics **v8.4.45** is a focused hotfix release that restores correct pretrained training behavior for `.pt` models, improves TensorRT and Jetson export reliability, and adds clearer docs for tuning and the Ultralytics Platform. 🎉

If you train from pretrained checkpoints such as **Ultralytics YOLO26** , this is an important update.

## 🔥 Highlights

### Critical training hotfix

The biggest fix in `v8.4.45` restores expected behavior for training from `.pt` checkpoints:

- `YOLO("model.pt").train()` now correctly starts from pretrained weights again
- CLI training also respects pretrained checkpoint defaults
- `pretrained=False` only disables weight loading when explicitly set
- Custom pretrained weight paths are preserved
- Classification scratch-training reset behavior was restored

This addresses a regression that could silently cause training to start without pretrained weights, costing both time and accuracy.

Implemented in [PR #24378](https://github.com/ultralytics/ultralytics/pull/24378) by [@glenn-jocher](https://github.com/glenn-jocher).

### Better TensorRT and Jetson reliability

This release also hardens deployment workflows:

- Blocked problematic `tensorrt==10.2.0` to avoid known runtime and export issues
- Unified TensorRT dependency checks with shared `check_tensorrt()`
- Improved JetPack 6 INT8 export reliability by upgrading TensorRT from 10.3 to 10.7 in Docker where needed
- Scoped automatic `end2end` disabling to the specific problematic combination: JetPack 6 + TensorRT 10.3.0 + INT8
- Added clearer warnings and troubleshooting guidance

These improvements are especially helpful for Jetson and TensorRT users deploying YOLO models in production.

## 🆕 New Features and Improvements

### Expanded export argument support

The `data` argument is now accepted for more export formats, helping dataset-aware INT8 and export workflows across:

- TensorRT
- OpenVINO
- CoreML
- TFLite
- TF.js
- MNN
- IMX

Added in [PR #24362](https://github.com/ultralytics/ultralytics/pull/24362) by [@lakshanthad](https://github.com/lakshanthad).

### Ultralytics Platform docs: Dataset Clustering

New docs were added for **Dataset Clustering** in the [Ultralytics Platform documentation](https://docs.ultralytics.com/platform/), making it easier to explore clusters, outliers, and duplicates interactively in 2D.

Added in [PR #24376](https://github.com/ultralytics/ultralytics/pull/24376) by [@sergiuwaxmann](https://github.com/sergiuwaxmann).

### Hyperparameter tuning docs update

The hyperparameter tuning guide was updated to better match current tuner behavior and outputs, reducing confusion for users tuning custom models.

Updated in [PR #24372](https://github.com/ultralytics/ultralytics/pull/24372) by [@raimbekovm](https://github.com/raimbekovm).

## 🛠 Bug Fixes

- Excluded problematic `tensorrt==10.2.0` in [PR #24367](https://github.com/ultralytics/ultralytics/pull/24367) by [@lakshanthad](https://github.com/lakshanthad)
- Auto-updated TensorRT from 10.3 to 10.7 on JetPack 6 systems for YOLO26 INT8 build issues in [PR #24368](https://github.com/ultralytics/ultralytics/pull/24368) by [@lakshanthad](https://github.com/lakshanthad)
- Applied `pretrained` argument handling across model trainers in [PR #24374](https://github.com/ultralytics/ultralytics/pull/24374) by [@glenn-jocher](https://github.com/glenn-jocher)
- Fixed pretrained checkpoint training regression in [PR #24378](https://github.com/ultralytics/ultralytics/pull/24378) by [@glenn-jocher](https://github.com/glenn-jocher)

## 🎯 Why this release matters

This update is small but important:

- ✅ Restores expected pretrained training behavior
- 🚀 Reduces avoidable TensorRT and Jetson deployment failures
- 🧰 Improves export workflows with broader `data` argument support
- 📚 Makes documentation more accurate and useful

For anyone training from `.pt` checkpoints or exporting models for edge deployment, `v8.4.45` is recommended.

## 📦 Get the release

You can review the full release in the [v8.4.45 release page](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.45) and browse all changes in the [full changelog from v8.4.43 to v8.4.45](https://github.com/ultralytics/ultralytics/compare/v8.4.43...v8.4.45).

## 💬 Try it and let us know

Please give **Ultralytics v8.4.45** a try and share your feedback, especially if you use pretrained `.pt` training, TensorRT export, Jetson, or the Ultralytics Platform.

Thanks to everyone in the YOLO community and to all contributors who helped improve this release! 🙌