我正在尝试在另一个Keras网络(B)中使用Keras网络(A)。我先培训网络A.然后我在网络B中使用它来执行一些正则化。内部网络BI希望使用evaluate
或predict
来获取网络A的输出。不幸的是我无法使其工作,因为这些函数需要一个numpy数组,而是接收它一个Tensorflow变量作为输入。
以下是我在自定义规范制定者中使用网络A的方法:
class CustomRegularizer(Regularizer):
def __init__(self, model):
"""model is a keras network"""
self.model = model
def __call__(self, x):
"""Need to fix this part"""
return self.model.evaluate(x, x)
如何计算带有Tensorflow变量作为输入的Keras网络的正向传递?
作为一个例子,这是我用numpy得到的:
x = np.ones((1, 64), dtype=np.float32)
model.predict(x)[:, :10]
输出:
array([[-0.0244251 , 3.31579041, 0.11801113, 0.02281714, -0.11048832,
0.13053198, 0.14661783, -0.08456061, -0.0247585 ,
0.02538805]], dtype=float32)
使用Tensorflow
x = tf.Variable(np.ones((1, 64), dtype=np.float32))
model.predict_function([x])
输出:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-92-4ed9d86cd79d> in <module>()
1 x = tf.Variable(np.ones((1, 64), dtype=np.float32))
----> 2 model.predict_function([x])
~/miniconda/envs/bolt/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
2266 updated = session.run(self.outputs + [self.updates_op],
2267 feed_dict=feed_dict,
-> 2268 **self.session_kwargs)
2269 return updated[:len(self.outputs)]
2270
~/miniconda/envs/bolt/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
776 try:
777 result = self._run(None, fetches, feed_dict, options_ptr,
--> 778 run_metadata_ptr)
779 if run_metadata:
780 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~/miniconda/envs/bolt/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
952 np_val = subfeed_val.to_numpy_array()
953 else:
--> 954 np_val = np.asarray(subfeed_val, dtype=subfeed_dtype)
955
956 if (not is_tensor_handle_feed and
~/miniconda/envs/bolt/lib/python3.6/site-packages/numpy/core/numeric.py in asarray(a, dtype, order)
529
530 """
--> 531 return array(a, dtype, copy=False, order=order)
532
533
ValueError: setting an array element with a sequence.
答案 0 :(得分:1)
我在keras博客文章中找到了答案。 https://blog.keras.io/keras-as-a-simplified-interface-to-tensorflow-tutorial.html
from keras.models import Sequential
model = Sequential()
model.add(Dense(32, activation='relu', input_dim=784))
model.add(Dense(10, activation='softmax'))
# this works!
x = tf.placeholder(tf.float32, shape=(None, 784))
y = model(x)
答案 1 :(得分:0)
我不确定tensorflow变量的位置,但是如果它在那里,你可以这样做:
model.predict([sess.run(x)])
其中sess
是张量流会话,即sess = tf.Session()
。