Tensorflow 从张量流估计器获得层激活

我有一个神经网络张量流估计器，我称之为分类器，我想打印出网络中一个叫做pool5的层的激活

在model函数中，我调用：

if mode == tf.estimator.ModeKeys.PREDICT:
    predictions = {"last_layer": pool5}
    return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions)

然后在主脚本中，我有

predictions = classifier.predict(input_fn=input_fn)
print(predictions["last_layer"])

但我得到的错误是

Traceback (most recent call last):
  File "C:/Users/John/AppData/Local/Programs/Python/Python35/Scripts/Estimator_5minutes.py", line 177, in <module>
    tf.app.run()
  File "C:\Users\John\AppData\Local\Programs\Python\Python35\lib\site-packages\tensorflow\python\platform\app.py", line 124, in run
    _sys.exit(main(argv))
  File "C:/Users/John/AppData/Local/Programs/Python/Python35/Scripts/Estimator_5minutes.py", line 152, in main
    print(predictions["last_layer"])
TypeError: 'generator' object is not subscriptable

---

这可能不是一个完美的答案，但以下是我为解决这个问题所做的

predictions = list(classifier.predict(input_fn=input_fn))
scipy.io.savemat('C:/activations.mat', {"activations": predictions})