TensorFlow2.1.0报错解决:AttributeError: ‘Sequential’ object has no attribute ‘_get_d

本机环境: cudatoolkit = 10.1.243 cudnn = 7.6.5 tensorflow-gpu = 2.1.0 keras-gpu = 2.3.1 今天在以TensorFlow2.1.0为后端的Keras中使用TensorBoard时报错,发现原因是keras和tf.keras混用导致的。报错与解决方案如下: 导致报错语句: summary = TensorBoard(log_dir="cnn_lstm_logs/",histogram_freq=1) 报错: ---> 54 summary = TensorBoard(log_dir="cnn_lstm_