Created by: siyangbing

W1231 10:56:15.739400 3785 device_context.cc:235] Please NOTE: device: 0, CUDA Capability: 61, Driver API Version: 10.1, Runtime API Version: 10.0 W1231 10:56:15.741755 3785 device_context.cc:243] device: 0, cuDNN Version: 7.3. W1231 10:56:15.741771 3785 device_context.cc:269] WARNING: device: 0. The installed Paddle is compiled with CUDNN 7.4, but CUDNN version in your machine is 7.3, which may cause serious incompatible bug. Please recompile or reinstall Paddle with compatible CUDNN version. W1231 10:56:16.498123 3785 naive_executor.cc:43] The NaiveExecutor can not work properly if the cmake flag ON_INFER is not set. W1231 10:56:16.498152 3785 naive_executor.cc:45] Unlike the training phase, all the scopes and variables will be reused to save the allocation overhead. W1231 10:56:16.498155 3785 naive_executor.cc:48] Please re-compile the inference library by setting the cmake flag ON_INFER=ON if you are running Paddle Inference

W1231 10:56:27.539149 3785 naive_executor.cc:43] The NaiveExecutor can not work properly if the cmake flag ON_INFER is not set. W1231 10:56:27.539177 3785 naive_executor.cc:45] Unlike the training phase, all the scopes and variables will be reused to save the allocation overhead. W1231 10:56:27.539180 3785 naive_executor.cc:48] Please re-compile the inference library by setting the cmake flag ON_INFER=ON if you are running Paddle Inference