Keras model.save() 和 model.save_weights() 的区别?

问题描述

在Keras中保存模型，输出文件有什么区别:

To save a model in Keras, what are the differences between the output files of:

1. model.save()
2. model.save_weights()
3. ModelCheckpoint() 在回调中

1. model.save()
2. model.save_weights()
3. ModelCheckpoint() in the callback

model.save() 中保存的文件比 model.save_weights() 中的模型大，但明显大于 JSON 或 Yaml 模型架构文件.为什么是这样?

The saved file from model.save() is larger than the model from model.save_weights(), but significantly larger than a JSON or Yaml model architecture file. Why is this?

重申这一点:为什么 size(model.save()) + size(something) = size(model.save_weights()) + size(model.to_json())，那是什么东西"?

Restating this: Why is size(model.save()) + size(something) = size(model.save_weights()) + size(model.to_json()), what is that "something"?

仅使用 model.save_weights() 和 model.to_json() 并从中加载是否比仅执行 model.save 更有效() 和 load_model()?

Would it be more efficient to just model.save_weights() and model.to_json(), and load from these than to just do model.save() and load_model()?

有什么区别?

推荐答案

save() 将权重和模型结构保存到单个 HDF5 文件中.我相信它还包括优化器状态之类的东西.然后您可以使用带有 load() 的 HDF5 文件来重建整个模型，包括权重.

save() saves the weights and the model structure to a single HDF5 file. I believe it also includes things like the optimizer state. Then you can use that HDF5 file with load() to reconstruct the whole model, including weights.

save_weights() 仅将权重保存到 HDF5，没有其他任何内容.您需要额外的代码来从 JSON 文件重建模型.

save_weights() only saves the weights to HDF5 and nothing else. You need extra code to reconstruct the model from a JSON file.

这篇关于Keras model.save() 和 model.save_weights() 的区别?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！