# \#pose
**URL:** https://community.ultralytics.com/tag/pose/39.md
[Latest](https://community.ultralytics.com/latest.md) · [Categories](https://community.ultralytics.com/categories.md) · [Tags](https://community.ultralytics.com/tags.md)
---
## [Feature vector shape in TensorRT converted pose estimation model?](https://community.ultralytics.com/t/feature-vector-shape-in-tensorrt-converted-pose-estimation-model/912)
**Author:** [@tw0trickp0ny](https://community.ultralytics.com/u/tw0trickp0ny)\
**Replies:** 4\
**Last updated:** [April 1, 2025, 12:53am UTC](https://community.ultralytics.com/t/feature-vector-shape-in-tensorrt-converted-pose-estimation-model/912 "2025-04-01T00:53:07Z")
Hi all, I recently converted a yolo11n-pose model to TensorRT (by first exporting to ONNX in python and then using trtexec). Now I’m running inference on it using a modified version of CyrusBehr’s tensorrt library for c…
---
## [YOLOv11 pose](https://community.ultralytics.com/t/yolov11-pose/563)
**Author:** [@sara](https://community.ultralytics.com/u/sara)\
**Replies:** 2\
**Last updated:** [December 4, 2024, 6:12am UTC](https://community.ultralytics.com/t/yolov11-pose/563 "2024-12-04T06:12:25Z")
I am using the YOLOv11 pose model for cabbage head detection. After running the prediction with the best weights, the size of the keypoints is very large. How can I adjust the keypoint size to match the original? This i…
---
## [Understanding Keypoint Decode](https://community.ultralytics.com/t/understanding-keypoint-decode/357)
**Author:** [@Daan\_Seuntjens](https://community.ultralytics.com/u/Daan_Seuntjens)\
**Replies:** 6\
**Last updated:** [October 22, 2024, 1:29pm UTC](https://community.ultralytics.com/t/understanding-keypoint-decode/357 "2024-10-22T13:29:45Z")
In keypoint decode, we apply: kpts\_out \* 2 + anchor - 0.5 I assume -0.5 is to center to the middle of a pixel. However, I do not understand why in all decoding functions of keypoints, a factor \*2 is applied? Seems lik…