Skip to content

Add Fine-Tune YOLO26 on Pose Estimation Dataset notebook#439

Open
yashdivya5 wants to merge 1 commit into
roboflow:mainfrom
yashdivya5:add/yolo26-pose-estimation-notebook
Open

Add Fine-Tune YOLO26 on Pose Estimation Dataset notebook#439
yashdivya5 wants to merge 1 commit into
roboflow:mainfrom
yashdivya5:add/yolo26-pose-estimation-notebook

Conversation

@yashdivya5
Copy link
Copy Markdown

Summary

Adds a notebook for fine-tuning YOLO26 on custom pose estimation datasets.

Motivation

Roboflow notebooks already have YOLO26 for object detection and instance
segmentation. This completes the set by adding pose estimation — matching
the same coverage that exists for YOLOv8 and YOLO11.

What this notebook covers

  • Loading pretrained yolo26n-pose model
  • Downloading pose dataset from Roboflow Universe
  • Fine-tuning on custom keypoint data
  • Evaluating pose mAP50 and mAP50-95
  • Visualizing keypoints using Supervision annotators
  • Exporting to ONNX / TFLite / TensorRT

Testing

  • Tested on Google Colab with T4 GPU
  • All cells run end to end successfully

@review-notebook-app
Copy link
Copy Markdown

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@CLAassistant
Copy link
Copy Markdown

CLAassistant commented May 25, 2026

CLA assistant check
All committers have signed the CLA.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants