Question

我模型的相关部分如下：

let picker = CNContactPickerViewController()
picker.displayedPropertyKeys = [CNContactPhoneNumbersKey]

picker.predicateForEnablingContact = NSPredicate(format: "phoneNumbers.@count > 0")

picker.predicateForSelectionOfContact = NSPredicate(value: false) 

picker.predicateForSelectionOfProperty = NSPredicate(format: "key == 'phoneNumbers'")
picker.delegate = self

喂食：

input_sequence = tf.placeholder(tf.float32, [BATCH_SIZE, TIME_STEPS, PIXEL_COUNT + AUX_INPUTS])
output_actual = tf.placeholder(tf.float32, [BATCH_SIZE, OUTPUT_SIZE])

lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(CELL_SIZE, state_is_tuple=False)
stacked_lstm = tf.nn.rnn_cell.MultiRNNCell([lstm_cell] * CELL_LAYERS, state_is_tuple=False)

initial_state = state = stacked_lstm.zero_state(BATCH_SIZE, tf.float32)
outputs = []

with tf.variable_scope("LSTM"):
    for step in xrange(TIME_STEPS):
        if step > 0:
            tf.get_variable_scope().reuse_variables()
        cell_output, state = stacked_lstm(input_sequence[:, step, :], state)
        outputs.append(cell_output)

final_state = state

当我运行它时，我收到以下错误：

cross_entropy = tf.reduce_mean(-tf.reduce_sum(output_actual * tf.log(prediction), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(learning_rate=LEARNING_RATE).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(output_actual, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

with tf.Session() as sess:
    sess.run(tf.initialize_all_variables())
    numpy_state = initial_state.eval()

    for i in xrange(1, ITERATIONS):
        batch = DI.next_batch()

        print i, type(batch[0]), np.array(batch[1]).shape, numpy_state.shape

        if i % LOG_STEP == 0:
            train_accuracy = accuracy.eval(feed_dict={
                initial_state: numpy_state,
                input_sequence: batch[0],
                output_actual: batch[1]
            })

            print "Iteration " + str(i) + " Training Accuracy " + str(train_accuracy)

        numpy_state, train_step = sess.run([final_state, train_step], feed_dict={
            initial_state: numpy_state,
            input_sequence: batch[0],
            output_actual: batch[1]
            })

也许最奇怪的部分是这个错误被抛出第二次迭代，第一次完全没问题。我试图解决这个问题，所以任何帮助都会非常感激。

Answer 1

您正在将train_step变量重新分配给sess.run()结果的第二个元素（恰好是None）。因此，在第二次迭代中，train_step为None，这会导致错误。

幸运的是，修复很简单：

for i in xrange(1, ITERATIONS):

    # ...

    # Discard the second element of the result.
    numpy_state, _ = sess.run([final_state, train_step], feed_dict={
        initial_state: numpy_state,
        input_sequence: batch[0],
        output_actual: batch[1]
        })

Answer 2

发生此错误的另一个常见原因是，如果您包括摘要提取操作，但未编写任何摘要。

示例：

# tf.summary.scalar("loss", loss) # <- uncomment this line and it will work fine
summary_op = tf.summary.merge_all()
sess = tf.Session()
# ...
summary = sess.run([summary_op, ...], feed_dict={...}) # TypeError, summary_op is "None"!

更令人困惑的是，summary_op本身不是None，那只是从会话的run方法内部冒出来的错误。

Tensorflow TypeError：Fetch参数None无效类型<type'nonetype'=“”>？

2 个答案: