captcha_records.py not working?

[Gintasz]

captcha_records.py not working?

[nalakawula]

me, too. encounter an error.

(virt) [sumarsono@mesin-arch solver]$ python2 captcha_records.py 
Looking for images in './data/train_data'
Traceback (most recent call last):
  File "captcha_records.py", line 125, in <module>
    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
  File "/home/sumarsono/dahoam2017/virt/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "captcha_records.py", line 103, in main
    training_data = create_data_list(FLAGS.train_dir)
  File "captcha_records.py", line 92, in create_data_list
    image_gray = image.convert('L')
  File "/home/sumarsono/dahoam2017/virt/lib/python2.7/site-packages/PIL/Image.py", line 857, in convert
    self.load()
  File "/home/sumarsono/dahoam2017/virt/lib/python2.7/site-packages/PIL/ImageFile.py", line 231, in load
    "(%d bytes not processed)" % len(b))
IOError: image file is truncated (0 bytes not processed)

[yohanesgultom]

In case you haven't found out the solution for error below:

Looking for images in './data/train_data'
>> Writing ./data/train.tfrecords
Traceback (most recent call last):
  File "captcha_records.py", line 123, in <module>
    tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
  File "/Users/gintas/Downloads/dahoam2017-master/dahoam/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "captcha_records.py", line 102, in main
    conver_to_tfrecords(training_data, TRAIN_FILE)
  File "captcha_records.py", line 62, in conver_to_tfrecords
    label_raw = label_to_one_hot(label).tostring()
  File "captcha_records.py", line 42, in label_to_one_hot
    index.append(CHAR_SETS.index(c))
ValueError: substring not found

It simply because this line of code below (function create_data_list in captcha_records.py) try to use split the captcha file name using _ as separator:

label_name = os.path.basename(file_name).split('_')[0]

Simply change it to . solve the issue:

label_name = os.path.basename(file_name).split('.')[0]

As for the IOError, apparently your captcha images are not correctly generated as I don't faced such an error.

[nalakawula]

ok, i'll try tonight
.
thank you