Question

我创建了两个张量（一个取决于另一个）如下：

weights = tf.random_normal(shape=(3, 3, 1, 64))
filters = get_filters(weights)  # get_filters does some operation on weights

因此，在上述操作之后，权重和过滤器看起来像

<tf.Tensor 'random_normal_1:0' shape=(3, 3, 1, 64) dtype=float32>
<tf.Tensor 'filters_1/weights:0' shape=(5, 3, 3, 1, 64) dtype=float32>

现在，我将这些张量传递给以下函数

def get_alphas(weights, filters, no_filters=5,
               epochs=500, name=None):
    with tf.name_scope(name, default_name="alpha_scope"):
        weights = tf.reshape(weights, [-1], name="reshaped_weights")
        filters = tf.reshape(filters, [no_filters, -1], name="reshaped_binary_filters")
        alphas = tf.Variable(tf.zeros(shape=(no_filters, 1)), name="alphas")
        weighted_sum = tf.reduce_sum(tf.multiply(alphas, filters), axis=0, name="weighted_sum")
        error = tf.square(weights - weighted_sum, name="error")
        loss = tf.reduce_mean(tf.reshape(error, [-1]), name="loss")

        # Optimizer
        optimizer = tf.train.AdamOptimizer()
        training_op = optimizer.minimize(loss, name="training_op")
        print(tf.global_variables())
        init = tf.variables_initializer([alphas])
        with tf.Session() as sess:
            init.run()
            epoch = 0
            while epoch < epochs:
                _, loss_train = sess.run([training_op, loss])  # <-- this is where the error is generated

                print("\rIteration: {}/{} ({:.1f}%)  Loss: {:.5f}".format(
                      epoch+1, epochs,
                      epoch * 100 / epochs,
                      loss_train),
                  end="")
                epoch += 1
            return tf.convert_to_tensor(sess.run(alphas))

在致电get_alphas(weights, filters)时，我收到以下错误

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value alpha_scope/beta1_power
     [[Node: alpha_scope/beta1_power/read = Identity[T=DT_FLOAT, _class=["loc:@alpha_scope/alphas"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](alpha_scope/beta1_power)]]
     [[Node: alpha_scope/loss/_1 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_115_alpha_scope/loss", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

所以，我使用tf.global_variables()打印tensorflow中的所有变量，并且有一些我未定义的未知变量（beta1_power，beta2_power），这就是造成此错误的原因< / p>

[<tf.Variable 'alpha_scope/alphas:0' shape=(5, 1) dtype=float32_ref>,
<tf.Variable 'alpha_scope/beta1_power:0' shape=() dtype=float32_ref>,
<tf.Variable 'alpha_scope/beta2_power:0' shape=() dtype=float32_ref>,
<tf.Variable 'alpha_scope/alphas/Adam:0' shape=(5, 1) dtype=float32_ref>,
<tf.Variable 'alpha_scope/alphas/Adam_1:0' shape=(5, 1) dtype=float32_ref>]

任何想法，如何创建这些变量？或者如何初始化它们？我不能使用tf.global_variables_initializer()，因为它可能会重置一些可能处于状态的变量。

Answer 1

这些变量来自tf.train.AdamOptimizer（请参阅this question）。既然你做了

init = tf.variables_initializer([alphas])
...
init.run()

...您已初始化了alphas而非AdamOptimizer的广告位。如果您无法使用tf.global_variables_initializer()，则必须按名称手动获取所有这些变量并初始化所有这些变量。

张量流状态中的未知变量导致训练操作中的错误

1 个答案: