您的数据分布情况如何?第一个建议是对训练/测试拆分进行分层(这是链接以获取文档).

How the distribution of your data looks like? The first suggestion is to stratify train/test split (here is the link for the documentation).

第二个问题是，与模型的复杂性相比，您拥有多少数据?也许您的模型是如此复杂，以至于过拟合.您可以使用命令 model.summary()来查看可训练参数的数量

The second question is how much data do you have in comparison with the complexity of the model? Maybe, your model is so complex, that just do overfitting. You can use the command model.summary() to see the number of trainable parameters.