Created by: omtbreak

前提条件

条件1

在PaddleDetection训练得到的模型权重，由提供的export工具，将其转换得到serving_server、serving_client等文件

serving_server 中的serving_server_conf.prototxt

serving_client中的serving_client_conf.prototxt

条件2

同时已跑通部署示例，此示例是Paddle开发人员训练的cascade rcnn模型，并提供了serving_server和serving_client等文件，在服务器开启服务后，使用rpc方式调用

问题

在跑通示例后，将我们训练的条件1中的模型，在服务器上开启了部署，本地客户端代码未更改，重新运行得到ShapeError

--------------------------------------------
C++ Call Stacks (More useful to developers):
--------------------------------------------

------------------------------------------
Python Call Stacks (More useful to users):
------------------------------------------
  File "/home/chenbaicheng/.local/lib/python3.6/site-packages/paddle/fluid/framework.py", line 2525, in append_op
    attrs=kwargs.get("attrs", None))
  File "/home/chenbaicheng/.local/lib/python3.6/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op
    return self.main_program.current_block().append_op(*args, **kwargs)
  File "/home/chenbaicheng/.local/lib/python3.6/site-packages/paddle/fluid/layers/nn.py", line 1405, in conv2d
    "data_format": data_format,
  File "/home/chenbaicheng/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 162, in _conv_norm
    name=_name + '.conv2d.output.1')
  File "/home/chenbaicheng/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 430, in c1_stage
    name=_name)
  File "/home/chenbaicheng/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 451, in __call__
    res = self.c1_stage(res)
  File "/home/chenbaicheng/PaddleDetection/ppdet/modeling/architectures/cascade_rcnn.py", line 98, in build
    body_feats = self.backbone(im)
  File "/home/chenbaicheng/PaddleDetection/ppdet/modeling/architectures/cascade_rcnn.py", line 336, in test
    return self.build(feed_vars, 'test')
  File "tools/export_serving_model.py", line 190, in main
    test_fetches = model.test(feed_vars)
  File "tools/export_serving_model.py", line 209, in <module>
    main()

----------------------
Error Message Summary:
----------------------
Error: ShapeError: the input of Op(conv) should be 4-D or 5-D Tensor. But received: 2-D Tensor, the shape of input is [1, 3].
  [Hint: Expected in_dims.size() == 4 || in_dims.size() == 5 == true, but received in_dims.size() == 4 || in_dims.size() == 5:0 != true:1.] at (/paddle/paddle/fluid/operators/conv_op.cc:61)
  [operator < conv2d > error]