Upload app.py

app.py

@@ -131,11 +131,8 @@ def build_demo_classes_and_metadata(vocab, label_list):
 
     MetadataCatalog.pop("fcclip_demo_metadata", None)
     demo_metadata = MetadataCatalog.get("fcclip_demo_metadata")
-    demo_metadata.thing_classes = [c[0] for c in demo_thing_classes]
-    demo_metadata.stuff_classes = [
-        *demo_metadata.thing_classes,
-        *[c[0] for c in demo_stuff_classes],
-    ]
+    demo_metadata.thing_classes = demo_thing_classes
+    demo_metadata.stuff_classes = demo_thing_classes+demo_stuff_classes
     demo_metadata.thing_colors = demo_thing_colors
     demo_metadata.stuff_colors = demo_thing_colors + demo_stuff_colors
     demo_metadata.stuff_dataset_id_to_contiguous_id = {
@@ -156,7 +153,6 @@ def inference(image_path, vocab, label_list):
     vocab = vocab.replace(", ", ",").replace("; ", ";")
     demo_classes, demo_metadata = build_demo_classes_and_metadata(vocab, label_list)
     predictor.set_metadata(demo_metadata)
-
     im = cv2.imread(image_path)
     outputs = predictor(im)
     v = OpenVocabVisualizer(im[:, :, ::-1], demo_metadata, instance_mode=ColorMode.IMAGE)