评估张量流张量

Question

获取输出相对于输入的梯度， 可以使用

grads = tf.gradients(model.output, model.input)

毕业生 =

[<tf.Tensor 'gradients_81/dense/MatMul_grad/MatMul:0' shape=(?, 18) dtype=float32>]

这是一个模型，其中有 18 个连续输入和 1 个连续输出。

我假设，这是一个符号表达式，需要一个包含 18 个条目的列表才能将其提供给张量，以便它以浮点数形式给出导数。

我会用

Test =[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0]
with tf.Session() as sess:
    alpha = sess.run(grads, feed_dict = {model.input : Test})
    print(alpha)

但我得到了错误

FailedPreconditionError (see above for traceback): Error while reading resource variable dense_2/bias from Container: localhost. This could mean that the variable was uninitialized. Not found: Container localhost does not exist. (Could not find resource: localhost/dense_2/bias)
     [[Node: dense_2/BiasAdd/ReadVariableOp = ReadVariableOp[dtype=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](dense_2/bias)]]

怎么了？

编辑： 这是，以前发生过的事情：

def build_model():
    model = keras.Sequential([ 
            ...])
    optimizer = ...
    model.compile(loss='mse'... ) 
    return model 


model = build_model()
history= model.fit(data_train,train_labels,...)
loss, mae, mse = model.evaluate(data_eval,...)

---

目前的进展：

Test =[1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0,1.0]

with tf.Session() as sess:
    tf.keras.backend.set_session(sess)
    tf.initializers.variables(model.output)
    alpha = sess.run(grads, feed_dict = {model.input : Test})

也不行，报错：

TypeError: Using a `tf.Tensor` as a Python `bool` is not allowed. Use `if t is not None:` instead of `if t:` to test if a tensor is defined, and use TensorFlow ops such as tf.cond to execute subgraphs conditioned on the value of a tensor.

Answer 1

您正在尝试使用未初始化的变量。你所要做的就是添加

sess.run(tf.global_variables_initializer()) 

就在with tf.Session() as sess:之后

编辑： 你需要注册 Keras 的 session

with tf.Session() as sess:
    tf.keras.backend.set_session(sess)

并使用tf.initializers.variables(var_list) 而不是tf.global_variables_initializer()

见https://blog.keras.io/keras-as-a-simplified-interface-to-tensorflow-tutorial.html

编辑：

Test = np.ones((1, 18), dtype=np.float32)

inputs = layers.Input(shape=[18,])
layer = layers.Dense(10, activation='sigmoid')(inputs)
model = tf.keras.Model(inputs=inputs, outputs=layer)
model.compile(optimizer='adam', loss='mse')
checkpointer = tf.keras.callbacks.ModelCheckpoint(filepath='path/weights.hdf5')
model.fit(Test, nb_epoch=1, batch_size=1, callbacks=[checkpointer])
grads = tf.gradients(model.output, model.input)

with tf.Session() as sess:
    tf.keras.backend.set_session(sess)
    sess.run(tf.global_variables_initializer())
    model.load_weights('path/weights.hdf5')
    alpha = sess.run(grads, feed_dict={model.input: Test})
    print(alpha)

这显示了一致的结果