ultralytics 8.3.155 Fix YOLO-World set_classes() error after prediction (#21051)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Mohammed Yasin 2025-06-14 17:17:06 +06:00 committed by GitHub
parent 9fa9824c4b
commit 1784300ef7
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 2 deletions

View File

@ -1,6 +1,6 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
__version__ = "8.3.154"
__version__ = "8.3.155"
import os

View File

@ -880,7 +880,6 @@ class WorldModel(DetectionModel):
self.txt_feats = self.get_text_pe(text, batch=batch, cache_clip_model=cache_clip_model)
self.model[-1].nc = len(text)
@smart_inference_mode()
def get_text_pe(self, text, batch=80, cache_clip_model=True):
"""
Set classes in advance so that model could do offline-inference without clip model.