zakizhou / captcha Goto Github PK

Hi!
I was trying this solver but when creates the TFRecords it show the following error:

Any ideas?

Traceback (most recent call last):
File "CNN/captcha_generator.py", line 8, in
from captcha.image import ImageCaptcha
File "/home/hui/Downloads/CAPTCHA-master/CNN/captcha.py", line 20
tf.constant_initializer(value=0),
^
SyntaxError: positional argument follows keyword argument
you import "from captcha.image import ImageCaptcha", but it is not found in CAPTCHA.py, is it a separate module then where to import ImageCAPTCHA module?

hi , thanks for sharing your code with us , could you tell us how could we use the trained saved model ?????

Alphabets Possible?

I get the following error upon executing captcha_train.py. Suggest where could have this code gone wrong. I followed readme file to the dot.

Traceback (most recent call last):
  File "model/captcha_train.py", line 85, in <module>
    main()
  File "model/captcha_train.py", line 79, in main
    coord.join(threads)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/coordinator.py", line 389, in join
    six.reraise(*self._exc_info_to_raise)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/queue_runner_impl.py", line 238, in _run
    enqueue_callable()
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1231, in _single_operation_run
    target_list_as_strings, status, None)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 24375 values, but the requested shape has 24576
	 [[Node: Reshape = Reshape[T=DT_UINT8, Tshape=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](DecodeRaw, Reshape/shape)]]

Hi, zakizhou
I have a question about the calculation of accuracy.
a correct prediction means every chars in a image are correctly predicted.
for example, if label=[a,b,c,d] and prediction=[a,b,c,e], for one example the accuracy is 0, not 75%
am I right? hope your reply

Hello,
I've just got follow error after I tried to execute this command:
python model/captcha_train.py

Can you help with this? I am sorry if it is a silly question, but I am just getting started to work with TensorFlow...

Traceback (most recent call last):
File "model/captcha_train.py", line 82, in
main()
File "model/captcha_train.py", line 44, in main
loss = captcha_model.loss(logits, labels)
File "/home/samir/Downloads/CAPTCHA/model/captcha_model.py", line 123, in loss
cross_entropy_per_number = tf.nn.softmax_cross_entropy_with_logits(logits, labels)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/nn_ops.py", line 491, in softmax_cross_entropy_with_logits
precise_logits, labels, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_nn_ops.py", line 1427, in _softmax_cross_entropy_with_logits
features=features, labels=labels, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 703, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2319, in create_op
set_shapes_for_outputs(ret)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1711, in set_shapes_for_outputs
shapes = shape_func(op)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/nn_ops.py", line 603, in _SoftmaxCrossEntropyWithLogitsShape
input_shape = logits_shape.merge_with(labels_shape).with_rank(2)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_shape.py", line 641, in with_rank
raise ValueError("Shape %s must have rank %d" % (self, rank))
ValueError: Shape (128, 4, 10) must have rank 2

I have cloned your code and run in my computer. The loss decreased but the validation accuracy is around 11% and didn't increase. I don't understand why and am very confused. Do you have any insight into the problem? Thank you very much.

Hi zakizhou
This is a wonderful work, i would like to know that how much accuracy you have achieved on your model?

$ python ./captcha_train.py
WARNING:tensorflow:From /Library/Python/2.7/site-packages/tensorflow/python/util/tf_should_use.py:175: initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use tf.global_variables_initializer instead.
WARNING:tensorflow:From /Library/Python/2.7/site-packages/tensorflow/python/util/tf_should_use.py:175: initialize_local_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.
Instructions for updating:
Use tf.local_variables_initializer instead.
2017-07-19 14:22:41.402951: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 14:22:41.402975: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 14:22:41.402980: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-07-19 14:22:41.402984: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
Done training -- epoch limit reached
Time Consumption: 0:00:00.061753
Traceback (most recent call last):
File "./captcha_train.py", line 82, in
main()
File "./captcha_train.py", line 76, in main
coord.join(threads)
File "/Library/Python/2.7/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "/Library/Python/2.7/site-packages/tensorflow/python/training/queue_runner_impl.py", line 238, in _run
enqueue_callable()
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 1235, in _single_operation_run
target_list_as_strings, status, None)
File "/System/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/contextlib.py", line 24, in exit
self.gen.next()
File "/Library/Python/2.7/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.NotFoundError: ../images/tfrecords/train.tfrecords
[[Node: ReaderReadV2 = ReaderReadV2[_device="/job:localhost/replica:0/task:0/cpu:0"](TFRecordReaderV2, input_producer)]]

What is the reason for this error when I execute?

tensorflow '1.2.1'