Update app.py

app.py

@@ -8,8 +8,8 @@ from transformers import (
     AutoTokenizer,
     BlipForConditionalGeneration,
     BlipProcessor,
-    OwlViTForObjectDetection,
-    OwlViTProcessor,
+    OwlV2ForObjectDetection,
+    OwlV2Processor,
     SamModel,
     SamProcessor,
 )
@@ -85,8 +85,8 @@ def run_image_captioner(image, device):
 def run_segmentation(image, object_to_segment, device):
     # OWL-V2 for object detection
     owl_v2_model_id = "google/owlv2-base-patch16-ensemble"
-    processor = Owlv2Processor.from_pretrained(owl_vit_model_id)
-    od_model = Owlv2ForObjectDetection.from_pretrained(owl_vit_model_id).to(device)
+    processor = Owlv2Processor.from_pretrained(owl_v2_model_id)
+    od_model = Owlv2ForObjectDetection.from_pretrained(owl_v2_model_id).to(device)
     text_queries = [object_to_segment]
     inputs = processor(text=text_queries, images=image, return_tensors="pt").to(device)
     with torch.no_grad():