tf.keras set_weights ValueError:Weights for model sequential_1 have not yet been created.

Miraini

于 2021-03-13 15:24:42 发布

阅读量6.3k

点赞数 1

分类专栏： tensorflow 经验总结 python

本文链接：https://blog.youkuaiyun.com/h1181471308/article/details/114748411

版权

在尝试使用tf.keras的set_weights方法时遇到错误：`ValueError: Weights for model sequential_1 have not yet been created.`。该错误表明模型的权重尚未创建，权重通常在模型首次接收到输入时生成。解决方案是在调用set_weights之前，先无输入地运行一次目标模型（target_model），确保其创建权重。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

ValueError: Weights for model sequential_1 have not yet been created. Weights are created when the Model is first called on inputs or `build()` is called with an `input_shape`.

ValueError: Weights for model sequential_1 have not yet been created. Weights are created when the Model is first called on inputs or build() is called with an input_shape.
它说模型没创建权重，权重是模型首次调用的时候创建的。

报错的是这句：