Created by: HugoLian

我新下了sentiment的predict.sh 与 predict.py https://github.com/PaddlePaddle/Paddle/tree/develop/demo/sentiment 在这个网络中，可以对输入流进行预测输出。

但是我把predict.py移植到其他网络（这里是quick_start的网络结构）中，却报错:

I1231 00:18:59.383359  9473 Util.cpp:155] commandline:  --use_gpu=0 
I1231 00:18:59.383488  9473 Util.cpp:130] Calling runInitFunctions
I1231 00:18:59.383779  9473 Util.cpp:143] Call runInitFunctions done.
[WARNING 2016-12-31 00:19:00,650 networks.py:1438] `outputs` routine try to calculate network's inputs and outputs order. It might not work well.Please see follow log carefully.
[INFO 2016-12-31 00:19:00,650 networks.py:1466] The input order is [word]
[INFO 2016-12-31 00:19:00,651 networks.py:1472] The output order is [__maxid_layer_0__, __fc_layer_0__]
I1231 00:19:00.676092  9473 GradientMachine.cpp:123] Loading parameters from output/pass-00014
F1231 00:19:00.677177  9473 FullyConnectedLayer.cpp:86] Check failed: input.value The input of 'fc' layer must be matrix
*** Check failure stack trace: ***
    @     0x7f59b0e03868  google::LogMessage::Fail()
    @     0x7f59b0e037c0  google::LogMessage::SendToLog()
    @     0x7f59b0e03255  google::LogMessage::Flush()
    @     0x7f59b0e06016  google::LogMessageFatal::~LogMessageFatal()
    @     0x7f59b050654b  paddle::FullyConnectedLayer::forward()
    @     0x7f59b056feba  paddle::NeuralNetwork::forward()
    @     0x7f59b0459026  _wrap_GradientMachine_forward
    @           0x4b4cb9  PyEval_EvalFrameEx
    @           0x4b6b28  PyEval_EvalCodeEx
    @           0x4b5d10  PyEval_EvalFrameEx
    @           0x4b6b28  PyEval_EvalCodeEx
    @           0x4b5d10  PyEval_EvalFrameEx
    @           0x4b5fb8  PyEval_EvalFrameEx
    @           0x4b5fb8  PyEval_EvalFrameEx
    @           0x4b6b28  PyEval_EvalCodeEx
    @           0x4b6c52  PyEval_EvalCode
    @           0x4e1c7d  PyRun_FileExFlags
    @           0x4e3501  PyRun_SimpleFileExFlags
    @           0x4159dd  Py_Main
    @     0x7f59b961dbd5  __libc_start_main
    @           0x414b71  (unknown)
predict2.sh: line 27:  9469 Broken pipe             cat ./data2/data.test
      9473 Aborted                 (core dumped) | python predict2.py --tconf=$config --model=$model --label=$label --dict=./data2/dict.txt --batch_size=1`

请问有没有一个通用的方式可以处理数据流的预测输出？或者是我哪里配置的不对么？