tensorflow error: InvalidArgumentError: Shape mismatch in tuple component 1. Expected [1], got [5] - python-2.7

Question

I am trying to construct a batch of (wav_file, label) pair.
wav file labels and paths are listed in dev.csv.
below code is not working,
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import tensorflow as tf
FLAGS = tf.app.flags.FLAGS
threads = 1
batch_size = 5
global record_defaults
record_defaults = [['/Users/phoenix/workspace/dataset/data_thchs30/dev/A11_101.wav'], ['8.26'], ['七十 年代 末 我 外出 求学 母亲 叮咛 我 吃饭 要 细嚼慢咽 学习 要 深 钻 细 研']]
def read_record(filename_queue, num_records):
reader = tf.TextLineReader()
key, value = reader.read_up_to(filename_queue, num_records)
wav_filename, duration, transcript = tf.decode_csv(value, record_defaults, field_delim=",")
wav_reader = tf.WholeFileReader()
wav_key, wav_value = wav_reader.read_up_to(tf.train.string_input_producer(wav_filename, shuffle=False, capacity=num_records), num_records)
return [wav_key, transcript] # throw errors
# return [wav_key, wav_value] # works
# return [wav_filename, duration, transcript] # works
data_queue = tf.train.string_input_producer(tf.train.match_filenames_once('dev.csv'), shuffle=False)
batch_data = [read_record(data_queue, batch_size) for _ in range(threads)]
capacity = threads * batch_size
batch_values = tf.train.batch_join(batch_data, batch_size=batch_size, capacity=capacity, enqueue_many=True)
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
sess.run(tf.initialize_local_variables())
coord = tf.train.Coordinator()
print(coord)
threads = tf.train.start_queue_runners(coord=coord)
print("threads num: " + str(threads))
try:
step = 0
while not coord.should_stop():
step += 1
feat = sess.run([batch_values])
print("line:", step, feat)
except tf.errors.OutOfRangeError:
print(' training for 1 epochs, %d steps', step)
finally:
coord.request_stop()
coord.join(threads)
throw errors below, how can I fix it?:
dev.csv content as below:
/Users/phoenix/workspace/dataset/data_thchs30/dev/A11_101.wav,8.26,qi shi nian dai mo wo wai chu qiu xue
/Users/phoenix/workspace/dataset/data_thchs30/dev/A11_119.wav,6.9,chen yun tong shi yao qiu gan bu men ren zhen xue xi

Answer 1

I tried to rewrite your code like this.
This is my observation.
The error is no longer thrown. And the values are returned.
An obvious discrepancy is that the size of the batch for transcript is double that specified. So it is 4 instead of 2. It doubles for some reason. No such problem for the audio binary.
shapes=[tf.TensorShape(()),tf.TensorShape(batch_size,)] is based on an error I saw which mentioned that I have to specify this using TensorShape. I didn't find the documentation of any help but it is mentioned there.
shapes: (Optional.) A list of fully-defined TensorShape objects with the same length as dtypes, or None.
import tensorflow as tf
tf.logging.set_verbosity(tf.logging.DEBUG)
FLAGS = tf.app.flags.FLAGS
threads = 1
batch_size = 2
record_defaults = [['D:/male.wav'], ['8.26'], ['七十 年代 末 我 外出 求学 母亲 叮咛 我 吃饭 要 细嚼慢咽 学习 要 深 钻 细 研']]
def readbatch(data_queue) :
reader = tf.TextLineReader()
_, rows = reader.read_up_to(data_queue, batch_size)
wav_filename, duration, transcript = tf.decode_csv(rows, record_defaults,field_delim=",")
audioreader = tf.WholeFileReader()
_, audio = audioreader.read( tf.train.string_input_producer(wav_filename) )
return [audio,transcript]
data_queue = tf.train.string_input_producer(
tf.train.match_filenames_once('D:/Book1.csv'), shuffle=False)
batch_data = [readbatch(data_queue) for _ in range(threads)]
capacity = threads * batch_size
batch_values = tf.train.batch_join(batch_data, shapes=[tf.TensorShape(()),tf.TensorShape(batch_size,)], capacity=capacity, batch_size=batch_size, enqueue_many=False )
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
sess.run(tf.initialize_local_variables())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
try:
step = 0
while not coord.should_stop():
step += 1
feat = sess.run([batch_values])
audio = feat[0][0]
print ('Size of audio is ' + str(audio.size))
script = feat[0][1]
print ('Size of script is ' + str(script.size))
except tf.errors.OutOfRangeError:
print(' training for 1 epochs, %d steps', step)
finally:
coord.request_stop()
coord.join(threads)
A sample dataset proves that there is an extra pair.
[[array([b'Text2', b'Text1'], dtype=object), array([[b'Translation-1', b'Translation-2'],
[b'Translation-1', b'Translation-2']], dtype=object)]]