use transformers dev

app.py

@@ -24,7 +24,8 @@ def query_image(img, text_queries):
         outputs = model(**inputs)
 
     target_sizes = torch.Tensor([[768, 768]])
-    outputs = {k: val.cpu() for k, val in outputs.items()}
+    outputs.logits = outputs.logits.cpu()
+    outputs.pred_boxes = outputs.pred_boxes.cpu() 
     results = processor.post_process(outputs=outputs, target_sizes=target_sizes)
     boxes, scores, labels = results[0]["boxes"], results[0]["scores"], results[0]["labels"]