0

我已经弄清楚是什么导致了这个错误，这是由于标签和输出之间的不匹配，就像我正在做 8 类情感分类，我的标签是 (1,2,3,4,7,8,9,10)所以它无法将预测（1,2,3,4,5,6,7,8）与我的标签匹配，这就是它给出超出范围错误的原因。我的问题是，为什么它在这一行没有给我错误，c_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(logits,Y)在这种情况下它如何将标签与预测匹配，而不是在 in_top_k 中？我认为c_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(logits,Y)应该给我错误，因为预测和标签不一样。为什么我没有在交叉熵函数中得到目标超出范围错误？

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
import numpy as np
import math
import os
from nltk.tokenize import TweetTokenizer
batch = 500
start = 0
end = batch - 1
learning_rate = 0.2
num_classes = 8
path = "/home/indy/Downloads/aclImdb/train/pos"
time_steps = 250
embedding = 50

def get_embedding():
    gfile_path = os.path.join("/home/indy/Downloads/glove.6B", "glove.6B.50d.txt")
    f = open(gfile_path,'r')
    embeddings = {}
    for line in f:
        sp_value = line.split()
        word = sp_value[0]
        embedding = [float(value) for value in sp_value[1:]]
        embeddings[word] = embedding
    return embeddings

ebd = get_embedding()

def get_y(file_name):
    y_value = file_name.split('_')
    y_value = y_value[1].split('.')
    return y_value[0] 

def get_x(path,file_name):
    file_path = os.path.join(path,file_name)
    x_value = open(file_path,'r')
    for line in x_value:
        x_value = line.replace("<br /><br />","") 
        x_value = x_value.lower()
    tokeniz = TweetTokenizer()
    x_value = tokeniz.tokenize(x_value)
    padding = 250 - len(x_value)
    if padding > 0:
       p_value = ['pad' for i in range(padding)]
       x_value = np.concatenate((x_value,p_value))
    x_value = [ebd['value'] for value in x_value]

    return x_value

def  batch_f(path):
     directory = os.listdir(path)
     y = [get_y(directory[i]) for i in range(len(directory))]
     x = [get_x(path,directory[i]) for i in range(len(directory))]    
     return x,y


X = tf.placeholder(tf.float32, [batch,time_steps,embedding])
Y = tf.placeholder(tf.int32, [batch])

def build_nlp_model(x, _units, lstm_layers,num_classes):

     x = tf.transpose(x, [1, 0, 2])
     x = tf.reshape(x, [-1, embedding])
     x = tf.split(0, time_steps, x)


     lstm = tf.nn.rnn_cell.LSTMCell(num_units = _units, state_is_tuple = True)

     multi_lstm = tf.nn.rnn_cell.MultiRNNCell([lstm] * lstm_layers, state_is_tuple = True)

     outputs , state = tf.nn.rnn(multi_lstm,x, dtype = tf.float32)     

     weights = tf.Variable(tf.random_normal([_units,num_classes]))
     biases  = tf.Variable(tf.random_normal([num_classes]))

     logits = tf.matmul(outputs[-1], weights) + biases
     return logits

logits = build_nlp_model(X,400,4,num_classes)
c_loss = tf.nn.sparse_softmax_cross_entropy_with_logits(logits,Y)
loss = tf.reduce_mean(c_loss)



decayed_learning_rate = tf.train.exponential_decay(learning_rate,0,10000,0.9)
optimizer= tf.train.AdamOptimizer(decayed_learning_rate)
minimize_loss = optimizer.minimize(loss)



correct_predict = tf.nn.in_top_k(logits, Y, 1)
accuracy = tf.reduce_mean(tf.cast(correct_predict, tf.float32))


init = tf.initialize_all_variables()

with tf.Session() as sess:
     sess.run(init)
     for i in range(25):
         x, y = batch_f(path)
         sess.run(minimize_loss,feed_dict={X : x, Y : y})
         accu = sess.run(accuracy,feed_dict = {X: x, Y: y})
         cost = sess.run(loss,feed_dict = {X: x,Y: y})
         start = end 
         end = (start + batch)
         print ("Minibatch Loss = " + "{:.6f}".format(cost) + ", Training Accuracy= " + "{:.5f}".format(accu))

这是错误堆栈。

(500, 250, 50)
(500,)
Traceback (most recent call last):
  File "nlp.py", line 115, in <module>
    accu = sess.run(accuracy,feed_dict = {X: x, Y: y})
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 372, in run
    run_metadata_ptr)
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 636, in _run
    feed_dict_string, options, run_metadata)
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 708, in _do_run
    target_list, options, run_metadata)
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 728, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors.InvalidArgumentError: targets[0] is out of range
     [[Node: InTopK = InTopK[T=DT_INT32, k=1, _device="/job:localhost/replica:0/task:0/cpu:0"](add, _recv_Placeholder_1_0)]]
Caused by op u'InTopK', defined at:
  File "nlp.py", line 102, in <module>
    correct_predict = tf.nn.in_top_k(logits, Y, 1)
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 890, in in_top_k
    targets=targets, k=k, name=name)
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/op_def_library.py", line 704, in apply_op
    op_def=op_def)
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2260, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/indy/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1230, in __init__
    self._traceback = _extract_stack()
4

0 回答 0