an error

[SJHBXShub]

Hi, wu
I confront this error when I run train.py. Do you know how to solved this problem?

Traceback (most recent call last):
File "train.py", line 50, in
sess.run( train_op,feed_dict={image: batch_inputs,train_output: batch_target_in,target_output: batch_target_out,sample_rate:np.min([1.,0.2*cur_e
poch+0.2])})
File "/home/sjhbxs/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 789, in run
run_metadata_ptr)
File "/home/sjhbxs/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 997, in _run
feed_dict_string, options, run_metadata)
File "/home/sjhbxs/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1132, in _do_run
target_list, options, run_metadata)
File "/home/sjhbxs/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1152, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: The node 'gradients/decode/decoder/while/BasicDecoderStep/ScheduledEmbeddingTrainingHe
lperSample_1/cond/Gather_1_grad/ExpandDims/StackPush' has inputs from different frames. The input 'gradients/decode/decoder/while/BasicDecoderStep/S
cheduledEmbeddingTrainingHelperSample_1/cond/Gather_1_grad/Size' is in frame ''. The input 'gradients/decode/decoder/while/BasicDecoderStep/Schedule
dEmbeddingTrainingHelperSample_1/cond/Gather_1_grad/ExpandDims/StackPush/Switch' is in frame 'decode/decoder/while/decode/decoder/while/'.

[SJHBXShub]

Hi, wu
I have solved this problem by deleting line 10 in train.py(with tf.control_dependencies(update_ops):)
Hope this suggestion will help others

Brs

[wushilian]

@SJHBXShub Thank you,I will fix this error