restore model 问题

[Canisantarcticus]

Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA 2018-10-09 10:11:06.422871: E tensorflow/stream_executor/cuda/cuda_driver.cc:406] failed call to cuInit: CUDA_ERROR_NO_DEVICE 2018-10-09 10:11:06.422917: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:158] retrieving CUDA diagnostic information for host: omnisky 2018-10-09 10:11:06.422927: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:165] hostname: omnisky 2018-10-09 10:11:06.422956: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:189] libcuda reported version is: 390.48.0 2018-10-09 10:11:06.422976: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:369] driver version file contents: """NVRM version: NVIDIA UNIX x86_64 Kernel Module 390.48 Thu Mar 22 00:42:57 PDT 2018 GCC version: gcc version 5.4.0 20160609 (Ubuntu 5.4.0-6ubuntu1~16.04.9) """ 2018-10-09 10:11:06.422993: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:193] kernel reported version is: 390.48.0 2018-10-09 10:11:06.423002: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:300] kernel version seems to match DSO: 390.48.0 restore model it is stop.请问是哪里出现错误导致的？ thank you very much !

[yangxue0827]

tfrecord可能是空的，读不出数据。 @Canisantarcticus

[yangxue0827]

Recommend improved code: https://github.com/DetectionTeamUCAS/FPN_Tensorflow. @Canisantarcticus

[ysssghtz]

have you solved this problem? I also encounter this question......