when i train the model，it raise an error,please help me!

[lzx168]

20/10000 [..............................] - ETA: 1:00:01 - loss: 2282.6917
40/10000 [..............................] - ETA: 31:47 - loss: 1886.1443
60/10000 [..............................] - ETA: 22:25 - loss: 1565.0140
80/10000 [..............................] - ETA: 17:43 - loss: 1411.5662
100/10000 [..............................] - ETA: 14:52 - loss: 1321.03732017-12-18 09:00:46.923191: W tensorflow/core/framework/op_kernel.cc:1152] Invalid argument: Saw a non-null label (index >= num_classes - 1) following a null label, batch: 10 num_classes: 73 labels: 1,43,27,1,6,22,1,27,21,5,54,41,8,28,37,4,32,38,1,13,34,2,41,28,1,15,19,1,46,13,2,24,6,1,13,65,4,19,47,1,51,10,1,31,28,8,63,39,4,37,21,4,42,12,3,17,38,5,57,68,1,13,39,1,13,68,1,13,30,1,30,16,71
Traceback (most recent call last):
File "/home/dell/sourcecode/aa/speech_to_text_train.py", line 120, in
batch_size=20,epochs=1000);
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1631, in fit
validation_steps=validation_steps)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1213, in _fit_loop
outs = f(ins_batch)
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 2332, in call
**self.session_kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Saw a non-null label (index >= num_classes - 1) following a null label, batch: 10 num_classes: 73 labels: 1,43,27,1,6,22,1,27,21,5,54,41,8,28,37,4,32,38,1,13,34,2,41,28,1,15,19,1,46,13,2,24,6,1,13,65,4,19,47,1,51,10,1,31,28,8,63,39,4,37,21,4,42,12,3,17,38,5,57,68,1,13,39,1,13,68,1,13,30,1,30,16,71
[[Node: ctc/CTCLoss = CTCLoss[ctc_merge_repeated=true, preprocess_collapse_repeated=false, _device="/job:localhost/replica:0/task:0/cpu:0"](ctc/Log/_1659, ctc/ToInt64/_1661, ctc/ToInt32_2/_1663, ctc/ToInt32_1/_1665)]]
[[Node: training/Adam/gradients/ctc/CTCLoss_grad/mul/_1693 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_20095_training/Adam/gradients/ctc/CTCLoss_grad/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]]

Caused by op u'ctc/CTCLoss', defined at:
File "/home/dell/sourcecode/aa/speech_to_text_train.py", line 110, in
loss_out=Lambda(ctc_lambda_function,output_shape=(1,),name="ctc")([y_true_input,logit,logit_length_input,y_true_length_input])
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 603, in call
output = self.call(inputs, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/keras/layers/core.py", line 651, in call
return self.function(inputs, **arguments)
File "/home/dell/sourcecode/aa/speech_to_text_train.py", line 99, in ctc_lambda_function
return K.ctc_batch_cost(y_true_input,logit,logit_length_input,y_true_length_input);
File "/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.py", line 3745, in ctc_batch_cost
sequence_length=input_length), 1)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/ctc_ops.py", line 145, in ctc_loss
ctc_merge_repeated=ctc_merge_repeated)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_ctc_ops.py", line 164, in _ctc_loss
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1228, in init
self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Saw a non-null label (index >= num_classes - 1) following a null label, batch: 10 num_classes: 73 labels: 1,43,27,1,6,22,1,27,21,5,54,41,8,28,37,4,32,38,1,13,34,2,41,28,1,15,19,1,46,13,2,24,6,1,13,65,4,19,47,1,51,10,1,31,28,8,63,39,4,37,21,4,42,12,3,17,38,5,57,68,1,13,39,1,13,68,1,13,30,1,30,16,71
[[Node: ctc/CTCLoss = CTCLoss[ctc_merge_repeated=true, preprocess_collapse_repeated=false, _device="/job:localhost/replica:0/task:0/cpu:0"](ctc/Log/_1659, ctc/ToInt64/_1661, ctc/ToInt32_2/_1663, ctc/ToInt32_1/_1665)]]
[[Node: training/Adam/gradients/ctc/CTCLoss_grad/mul/_1693 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_20095_training/Adam/gradients/ctc/CTCLoss_grad/mul", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]]

Process finished with exit code 1

[moneypi]

same problem,anyone help?

[zhaowz]

the author use python3, so char_index will have 2665 character.
in python 2.x，you need decode word:
all_words=[]
for i in np.arange(0,len(texts)):
for j in np.arange(1,len(texts[i])):
all_words.append(texts[i][j])
all_words=[i.decode() for i in all_words]