加速TensorFlow的初始启动

每次我使用TensorFlow(CPU)运行Python代码时,例如:

import keras

我看到这个:

2020-10-30 15:27:20.518894: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'cudart64_101.dll'; dlerror: cudart64_101.dll not found
2020-10-30 15:27:20.518894: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
2020-10-30 15:27:23.713077: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2020-10-30 15:27:23.713077: E tensorflow/stream_executor/cuda/cuda_driver.cc:313] failed call to cuInit: UNKNOWN ERROR (303)
2020-10-30 15:27:23.716077: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: User1-PC
2020-10-30 15:27:23.716077: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: User1-PC
2020-10-30 15:27:23.729078: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x10cad0c0 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-10-30 15:27:23.729078: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
Using TensorFlow backend.

如果我把所有的等待时间加起来,大约有10秒的等待时间。

有没有办法加快这一进程? 特别是如果我使用TensorFlow进行推理(而不是训练),我不想在每次启动引擎时等待10秒。

注意:当然,当我的代码准备就绪时,我会使用TensorFlow保持进程不断运行,并使用某种进程间通信,以避免重新启动整个程序。

我在这里的问题主要是 原型制作 阶段,当你 经常 需要重新启动程序:在原型制作时,每次脚本启动都要等待10或15秒,这非常不方便。