我如何获得中间层的输出（tensor2tensor中的特征提取）？

Question

推断后，我需要查看中间值，类似于Keras的建议[here] [1]

https://keras.io/getting_started/faq/#how-can-i-obtain-the-output-of-an-intermediate-layer-feature-extraction

 model = ...  # create the original model

 layer_name = 'my_layer'
 intermediate_layer_model = keras.Model(inputs=model.input,
                                       outputs=model.get_layer(layer_name).output)
 intermediate_output = intermediate_layer_model(data) 

我在tensor2tensor中找不到类似的解决方案。是否可以设置hparam以在特定层切割模型？