Tensorflow设计的时候没有考虑多线程? 这问题好多年了没搞定。4天前还有人报告。 https://github.com/keras-team/keras/issues/2397 I'm still having this issue and the recommended fixes do not work for me. The only thing that works is loading the model and making a prediction with each prediction request. I'm requesting that this issue be reopened as no actual solution has been proposed, just several workarounds that seem to work intermittently. This fix does not seem to work when using custom graphs.
【在 g****t 的大作中提到】 : Tensorflow设计的时候没有考虑多线程? : 这问题好多年了没搞定。4天前还有人报告。 : https://github.com/keras-team/keras/issues/2397 : I'm still having this issue and the recommended fixes do not work for me. : The only thing that works is loading the model and making a prediction with : each prediction request. I'm requesting that this issue be reopened as no : actual solution has been proposed, just several workarounds that seem to : work intermittently. : This fix does not seem to work when using custom graphs.