python-2.7 - ValueError : Tensor Tensor ("Const:0", shape=(), dtype=float32) 可能无法与 tf.placeholder 一起提供

Question

我正在尝试用tensorflow制作语音识别系统。

• 输入数据是大小为 50000 X 1 的 numpy 数组。

• 输出数据(映射数据)是大小为 400 X 1 的 numpy 数组。

输入和映射数据在列表中以 2 为一组进行传递。

我用过this设计神经网络的教程。以下是代码片段:

对于 RNN:

input_data = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_DATA, sound_constants.MAX_COLUMN_SIZE_IN_DATA], name="train_input")
target = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT], name="train_output")

fwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)

# creating one backward cell
bkwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)

# creating bidirectional RNN
val, _, _ = tf.nn.static_bidirectional_rnn(fwd_cell, bkwd_cell, tf.unstack(input_data), dtype=tf.float32)

用于馈送数据:

feed = {g['input_data'] : trb[0], g['target'] : trb[1], g['dropout'] : 0.6}
accuracy_, _ = sess.run([g['accuracy'], g['ts']], feed_dict=feed)
accuracy += accuracy_

当我运行代码时，出现以下错误:

Traceback (most recent call last):
  File "/home/wolborg/PycharmProjects/speech-to-text-rnn/src/rnn_train_1.py", line 205, in <module>
    tr_losses, te_losses = train_network(g)
  File "/home/wolborg/PycharmProjects/speech-to-text-rnn/src/rnn_train_1.py", line 177, in train_network
    accuracy_, _ = sess.run([g['accuracy'], g['ts']], feed_dict=feed)
  File "/home/wolborg/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run
    run_metadata_ptr)
  File "/home/wolborg/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1102, in _run
    raise ValueError('Tensor %s may not be fed.' % subfeed_t)
ValueError: Tensor Tensor("Const:0", shape=(), dtype=float32) may not be fed.

Process finished with exit code 1

早些时候，我在 tf.sparse_placeholder 上遇到了这个问题，然后经过一番浏览，我将输入类型更改为 tf.placeholder 并进行了相关更改。现在我不知道我在哪里犯了错误。

请建议我应该如何提供数据。

整个代码:

import tensorflow as tf

# for taking MFCC and label input
import numpy as np
import rnn_input_data_1
import sound_constants

# input constants

# Training Parameters
num_input = 10 # mfcc data input
training_data_size = 8 # determines number of files in training and testing module
testing_data_size = num_input - training_data_size

# Network Parameters
learning_rate = 0.0001 # for large training set, it can be set 0.001
num_hidden = 200 # number of hidden layers
num_classes = 28 # total alphabet classes (a-z) + extra symbols (', ' ')
epoch = 1 # number of iterations
batch_size = 2 # number of batches

mfcc_coeffs, text_data = rnn_input_data_1.mfcc_and_text_encoding()

class DataGenerator:
    def __init__(self, data_size):
    self.ptr = 0
    self.epochs = 0
    self.data_size = data_size

    def next_batch(self):
    self.ptr += batch_size
    if self.ptr > self.data_size:
        self.epochs += 1
        self.ptr = 0

    return mfcc_coeffs[self.ptr-batch_size : self.ptr], text_data[self.ptr-batch_size : self.ptr]

def reset_graph():
    if 'sess' in globals() and sess:
    sess.close()
    tf.reset_default_graph()

def struct_network():

    print ('Inside struct network !!')

    reset_graph()

    input_data = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_DATA, sound_constants.MAX_COLUMN_SIZE_IN_DATA], name="train_input")
    target = tf.placeholder(tf.float32, [batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT], name="train_output")

    keep_prob = tf.constant(1.0)

    fwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)

    # creating one backward cell
    bkwd_cell = tf.nn.rnn_cell.BasicLSTMCell(num_hidden, state_is_tuple=True, forget_bias=1.0)

    # creating bidirectional RNN
    val, _, _ = tf.nn.static_bidirectional_rnn(fwd_cell, bkwd_cell, tf.unstack(input_data), dtype=tf.float32)

    # adding dropouts
    val = tf.nn.dropout(val, keep_prob)

    val = tf.transpose(val, [1, 0, 2])
    last = tf.gather(val, int(val.get_shape()[0]) - 1)

    # creating bidirectional RNN
    print ('BiRNN created !!')


    print ('Last Size: ', last.get_shape())

    weight = tf.Variable(tf.truncated_normal([num_hidden * 2, sound_constants.MAX_ROW_SIZE_IN_TXT]))
    bias = tf.Variable(tf.constant(0.1, shape=[sound_constants.MAX_ROW_SIZE_IN_TXT]))

    # mapping to 28 output classes
    logits = tf.matmul(last, weight) + bias
    prediction = tf.nn.softmax(logits)
    prediction = tf.reshape(prediction, shape = [batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT])

    # getting probability distribution
    mat1 = tf.cast(tf.argmax(prediction,1),tf.float32)
    correct = tf.equal(prediction, target)
    accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))

    logits = tf.reshape(logits, shape=[batch_size, sound_constants.MAX_ROW_SIZE_IN_TXT, sound_constants.MAX_COLUMN_SIZE_IN_TXT])


    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=target))
    train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)

    # returning components as dictionary elements
    return {'input_data' : input_data,
        'target' : target,
        'dropout': keep_prob,
        'loss': loss,
        'ts': train_step,
        'preds': prediction,
        'accuracy': accuracy
        }


def train_network(graph):


    # initialize tensorflow session and all variables
    # tf_gpu_config = tf.ConfigProto(allow_soft_placement = True, log_device_placement = True)
    # tf_gpu_config.gpu_options.allow_growth = True


    # with tf.Session(config = tf_gpu_config) as sess:
    with tf.Session() as sess:

    train_instance = DataGenerator(training_data_size)
    test_instance = DataGenerator(testing_data_size)

    print ('Training data size: ', train_instance.data_size)
    print ('Testing data size: ', test_instance.data_size)

    sess.run(tf.global_variables_initializer())
    print ('Starting session...')
    step, accuracy = 0, 0
    tr_losses, te_losses = [], []
    current_epoch = 0
    while current_epoch < epoch:
        step += 1
        trb = train_instance.next_batch()

        feed = {g['input_data'] : trb[0], g['target'] : trb[1], g['dropout'] : 0.6}
        accuracy_, _ = sess.run([g['accuracy'], g['ts']], feed_dict=feed)
        accuracy += accuracy_

        if train_instance.epochs > current_epoch:
            current_epoch += 1
            tr_losses.append(accuracy / step)
            step, accuracy = 0, 0

            #eval test set
            te_epoch = test_instance.epochs
            while test_instance.epochs == te_epoch:
                step += 1
                print ('Testing round ', step)
                trc = test_instance.next_batch()
                feed = {g['input_data']: trc[0], g['target']: trc[1]}
                accuracy_ = sess.run([g['accuracy']], feed_dict=feed)[0]
                accuracy += accuracy_

            te_losses.append(accuracy / step)
            step, accuracy = 0,0
            print("Accuracy after epoch", current_epoch, " - tr:", tr_losses[-1], "- te:", te_losses[-1])

    return tr_losses, te_losses

g = struct_network()
tr_losses, te_losses = train_network(g)

Answer 1

您将 keep_prob 定义为 tf.constant，但随后尝试将值输入其中。将 keep_prob = tf.constant(1.0) 替换为 keep_prob = tf.placeholder(tf.float32,[]) 或 keep_prob = tf.placeholder_with_default(1.0,[ ])