miumiu2017的博客

原创 错误： tensorflow:Early stopping conditioned on metric `val_accuracy` which is not available

训练时错误： tensorflow:Early stopping conditioned on metric val_accuracy which is not available.keras搭建LSTM，加入Early stopping，出现的错误提示，我的解决方式是–减少model模型参数量，以减少对内存的消耗。分析原因（大概率）加了callbacks=加了内存消耗。...