fix text prompt

app.py

@@ -18,7 +18,7 @@ hence you can get better predictions by querying the image with text templates u
 demo = gr.Interface(
     query_image, 
     inputs=[gr.Image(), "text"], 
-    outputs="image",
+    outputs=["image", "image"],
     title="Zero-Shot Object Detection with OWL-ViT",
     description=description,
     examples=[

demo.py

@@ -87,7 +87,7 @@ def query_image(img, text_prompt):
         pil_img = Image.fromarray(np.uint8(img)).convert('RGB')
 
     text_prompt = text_prompt
-    texts = text_prompt.split(",")
+    texts = [text_prompt.split(",")]
 
     box_threshold = 0.0
 
@@ -115,11 +115,6 @@ def query_image(img, text_prompt):
     # boxes, scores, labels = results[i]["boxes"], results[i]["scores"], results[i]["labels"]
     
 
-    # Print detected objects and rescaled box coordinates
-    # for box, score, label in zip(boxes, scores, labels):
-    #     box = [round(i, 2) for i in box.tolist()]
-    #     print(f"Detected {text[label]} with confidence {round(score.item(), 3)} at location {box}")
-
     boxes = boxes.cpu().detach().numpy()
     normalized_boxes = copy.deepcopy(boxes)
     
@@ -174,5 +169,5 @@ def query_image(img, text_prompt):
     # grounded results
     image_with_box = plot_boxes_to_image(pil_img, pred_dict)[0]
     
-    # return owlvit_segment_image, image_with_box
-    return owlvit_segment_image
+    return owlvit_segment_image, image_with_box
+    # return owlvit_segment_image