updated get_caption

utils/Caption.py

@@ -7,7 +7,7 @@ def get_caption(image):
 
     model = AutoModel.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5', trust_remote_code=True, torch_dtype=torch.float16)
     model = model.to(device='cuda')
-
+    image.to(device='cuda')
     tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-Llama3-V-2_5', trust_remote_code=True)
     model.eval()
     question = "Describe the image."