There was an error when using a model from the mmyolo repository during image preprocessing, provided that an array was supplied as input. If you input the path to the image, everything works fine. (open-mmlab#2554)

Author: Danil328

mmdeploy/codebase/mmdet/deploy/object_detection.py

@@ -60,7 +60,7 @@ def process_model_config(model_cfg: Config,
     if isinstance(imgs[0], np.ndarray):
         cfg = cfg.copy()
         # set loading pipeline type
-        cfg.test_pipeline[0].type = 'LoadImageFromNDArray'
+        cfg.test_pipeline[0].type = 'mmdet.LoadImageFromNDArray'
 
     pipeline = cfg.test_pipeline