Elgato_dark/ultralytics
1
0
Fork 0
mirror of https://github.com/ultralytics/ultralytics synced 2026-05-24 09:38:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

ultralytics 8.3.93 Fix TorchScript Model with NMS loading error (#19747)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Mohammed Yasin 2025-03-19 06:15:29 +06:00 committed by GitHub
parent a85185b0ae
commit d97689fbf3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 4 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docs/en/models/yoloe.md
View file

@ -10,7 +10,7 @@ keywords: YOLOE, open-vocabulary detection, real-time object detection, instance
![YOLOE Prompting Options](https://github.com/THU-MIG/yoloe/raw/main/figures/visualization.svg)
[**YOLOE** (You Only Look Once **E**nhanced)](https://arxiv.org/html/2503.07465v1) is a new advancement in zero-shot, promptable YOLO models, designed for **open-vocabulary** detection and segmentation. Unlike previous YOLO models limited to fixed categories, YOLOE uses text, image, or internal vocabulary prompts, enabling real-time detection of any object class. Built upon YOLOv10 and inspired by [YOLO-World](https://docs.ultralytics.com/models/yolo-world/), YOLOE achieves **state-of-the-art zero-shot performance** with minimal impact on speed and accuracy.
[YOLOE (Real-Time Seeing Anything)](https://arxiv.org/html/2503.07465v1) is a new advancement in zero-shot, promptable YOLO models, designed for **open-vocabulary** detection and segmentation. Unlike previous YOLO models limited to fixed categories, YOLOE uses text, image, or internal vocabulary prompts, enabling real-time detection of any object class. Built upon YOLOv10 and inspired by [YOLO-World](https://docs.ultralytics.com/models/yolo-world/), YOLOE achieves **state-of-the-art zero-shot performance** with minimal impact on speed and accuracy.
!!! note "Ultralytics Integration Status 🚧"

2
ultralytics/__init__.py
View file

@ -1,6 +1,6 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
__version__ = "8.3.92"
__version__ = "8.3.93"
import os

2
ultralytics/nn/autobackend.py
View file

@ -185,6 +185,8 @@ class AutoBackend(nn.Module):
# TorchScript
elif jit:
import torchvision # noqa - https://github.com/ultralytics/ultralytics/pull/19747
LOGGER.info(f"Loading {w} for TorchScript inference...")
extra_files = {"config.txt": ""} # model metadata
model = torch.jit.load(w, _extra_files=extra_files, map_location=device)