在 keras 中保存和加载权重 [英] Save and load weights in keras

问题描述

我正在尝试从我训练的模型中保存和加载权重.

Im trying to save and load weights from the model i have trained.

我用来保存模型的代码是.

the code im using to save the model is.

TensorBoard(log_dir='/output')
model.fit_generator(image_a_b_gen(batch_size), steps_per_epoch=1, epochs=1)
model.save_weights('model.hdf5')
model.save_weights('myModel.h5')

让我知道这是否是一种不正确的方法，或者是否有更好的方法.

Let me know if this an incorrect way to do it,or if there is a better way to do it.

但是当我尝试加载它们时，使用这个，

but when i try to load them,using this,

from keras.models import load_model
model = load_model('myModel.h5')

但我收到此错误:

ValueError                                Traceback (most recent call 
last)
<ipython-input-7-27d58dc8bb48> in <module>()
      1 from keras.models import load_model
----> 2 model = load_model('myModel.h5')

/home/decentmakeover2/anaconda3/lib/python3.5/site-
packages/keras/models.py in load_model(filepath, custom_objects, compile)
    235         model_config = f.attrs.get('model_config')
    236         if model_config is None:
--> 237             raise ValueError('No model found in config file.')
    238         model_config = json.loads(model_config.decode('utf-8'))
    239         model = model_from_config(model_config, 
custom_objects=custom_objects)

ValueError: No model found in config file.

对我可能做错了什么有什么建议吗?提前致谢.

Any suggestions on what i may be doing wrong? Thank you in advance.

推荐答案

这是一个 YouTube 视频，它准确地解释了您想要做什么:保存和加载 Keras 模型

Here is a YouTube video that explains exactly what you're wanting to do: Save and load a Keras model

Keras 提供了三种不同的保存方法.这些在上面的视频链接(带有示例)和下面都有描述.

There are three different saving methods that Keras makes available. These are described in the video link above (with examples), as well as below.

首先，您收到错误的原因是您错误地调用了 load_model.

First, the reason you're receiving the error is because you're calling load_model incorrectly.

要保存和加载模型的权重，您首先要使用

To save and load the weights of the model, you would first use

model.save_weights('my_model_weights.h5')

保存权重，如您所显示的.要加载权重，您首先需要构建模型，然后在模型上调用 load_weights，如

to save the weights, as you've displayed. To load the weights, you would first need to build your model, and then call load_weights on the model, as in

model.load_weights('my_model_weights.h5')

另一种保存技术是model.save(filepath).这个 save 函数保存:

Another saving technique is model.save(filepath). This save function saves:

• 模型的架构，允许重新创建模型.
• 模型的权重.
• 训练配置(损失、优化器).
• 优化器的状态，允许从上次中断的地方继续训练.

要加载这个保存的模型，您可以使用以下内容:

To load this saved model, you would use the following:

from keras.models import load_model
new_model = load_model(filepath)'

最后，model.to_json()，只保存模型的架构.要加载架构，您将使用

Lastly, model.to_json(), saves only the architecture of the model. To load the architecture, you would use

from keras.models import model_from_json
model = model_from_json(json_string)

这篇关于在 keras 中保存和加载权重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IT屋！