Created by: zyz282994112

你好！我这边基于v2训练的模型里包含factorization_machine层。训练时没问题，但在使用capi做inference时，报“Unknown class type: factorization_machine”，如下图所示：

I0312 16:29:52.932291 14024 Util.cpp:166] commandline: --use_gpu=False W0312 16:29:52.932369 14024 CpuId.h:112] PaddlePaddle wasn't compiled to use avx instructions, but these are available on your machine and could speed up CPU computations via CMAKE .. -DWITH_AVX=ON F0312 16:29:53.734858 14024 ClassRegistrar.h:65] Check failed: mapGet(type, creatorMap_, &creator) Unknown class type: factorization_machine

* Check failure stack trace: *

@ 0x7f34e26b3aad google::LogMessage::Fail() @ 0x7f34e26b755c google::LogMessage::SendToLog() @ 0x7f34e26b35d3 google::LogMessage::Flush() @ 0x7f34e26b8a6e google::LogMessageFatal::~LogMessageFatal() @ 0x7f34e2783d0e paddle::Layer::create() @ 0x7f34e2820a30 ZZN6paddle13NeuralNetwork4initERKNS_11ModelConfigESt8functionIFviPNS_9ParameterEEERKSt6vectorINS_19enumeration_wrapper13ParameterTypeESaISB_EEbENKUlRKNS_11LayerConfigEE_clESI @ 0x7f34e2821e83 paddle::NeuralNetwork::init() @ 0x7f34e2832fa1 paddle::GradientMachine::create() @ 0x7f34e26b097f paddle_gradient_machine_create_for_inference_with_parameters @ 0x476c39 pme::ConsistentResource::init() @ 0x485069 pme::PaddleModel::try_reload() @ 0x485d33 pme::PaddleModel::init() @ 0x480dde pme::PaddlePredictEngine::initialize() @ 0x48735d pme::PMEServiceImpl::initialize() @ 0x465624 main @ 0x7f34e1514bd5 __libc_start_main @ 0x46e851 (unknown) @ (nil) (unknown) Aborted (core dumped)