在triton推断服务器上使用python在模型中执行获取问题json解析器

Question

python3 /home/ubuntu/Deepthi/triton-inference-server-master/src/clients/python/examples/image_client.py -m /home/ubuntu/Deepthi/triton-inference-server-master/docs/model_repository/resnet50_netdef/1 -s INCEPTION /home/ubuntu/Deepthi/triton-inference-server-master/qa/images/mug.jpg
Traceback (most recent call last):
  File "/home/ubuntu/Deepthi/triton-inference-server-master/src/clients/python/examples/image_client.py", line 403, in <module>
    model_name=FLAGS.model_name, model_version=FLAGS.model_version)
  File "/home/ubuntu/.local/lib/python3.6/site-packages/tritonhttpclient/__init__.py", line 471, in get_model_metadata
    _raise_if_error(response)
  File "/home/ubuntu/.local/lib/python3.6/site-packages/tritonhttpclient/__init__.py", line 57, in _raise_if_error
    error = _get_error(response)
  File "/home/ubuntu/.local/lib/python3.6/site-packages/tritonhttpclient/__init__.py", line 46, in _get_error
    error_response = json.loads(response.read())
rapidjson.JSONDecodeError: Parse error at offset 0: The document is empty.

我不明白为什么我会犯这个错误，一切都准备好了