使用keras在json中转储cnn的权重(dump weights of cnn in json using keras)

使用keras在json中转储cnn的权重(dump weights of cnn in json using keras)

我想在其他框架中使用转储的权重和模型架构进行测试。 我知道model.get_config（）可以给出模型的配置。 _json将模型的表示形式返回为JSO字符串。 但是表示不包括权重，只包括体系结构。 和model.save_weights（filepath）：将模型的权重保存为HDF5文件。 和model.save_weights（filepath）将模型的权重保存为HDF5文件。 我想在json文件中保存体系结构和权重。

I want to use the dumped weights and model architecture in other framework for testing.

I know that:

model.get_config() can give the configuration of the model _json returns a representation of the model as a JSO string, but that the representation does not include the weights, only the architecture model.save_weights(filepath) saves the weights of the model as a HDF5 file

I want to save the architecture as well as weights in a json file.

最满意答案

Keras没有任何内置方法可以将权重导出到JSO。

解决方案1：

现在，您可以通过迭代权重并将其保存到JSO文件来轻松完成。

weights_list = model.get_weights()

将返回模型中所有权重张量的列表，如umpy数组。

然后，接下来要做的就是迭代这个列表并写入文件：

for i, weights in enumerate(weights_list): writeJSO(weights)

解决方案2：

import json weights_list = model.get_weights() print json.dumps(weights_())

Keras does not have any built-in way to export the weights to JSO.

Solution 1:

For now you can easily do it by iterating over the weights and saving it to the JSO file.

weights_list = model.get_weights()

will return a list of all weight tensors in the model, as umpy arrays.

Then, all you have to do next is to iterate over this list and write to the file:

for i, weights in enumerate(weights_list): writeJSO(weights)

Solution 2:

import json weights_list = model.get_weights() print json.dumps(weights_())