bshao001
commented
5 years ago It is very likely that your data is having some kind of problem, but I cannot tell without looking at the details. You can google around, and I believe I have seen similar errors before from someone else.
I included some of your own data and my own data and created vocab file. But when I trained the model bottrainer.py it starts for running first epoch and then stops giving the error as: Traceback (most recent call last): File "bottrainer.py", line 161, in
bt.train(res_dir)
File "bottrainer.py", line 88, in train
step_result = self.model.train_step(sess, learning_rate=learning_rate)
File "/home/ruksin/PycharmProjects/chatlearner/chatbot/modelcreator.py", line 122, in train_step
feed_dict={self.learning_rate: learning_rate})
File "/home/ruksin/PycharmProjects/chatlearner/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/home/ruksin/PycharmProjects/chatlearner/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/home/ruksin/PycharmProjects/chatlearner/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/home/ruksin/PycharmProjects/chatlearner/venv/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: pos 0 out of range for stringb'' at index 0
[[Node: Substr = Substr[T=DT_INT32](arg0, Substr/pos, Substr/len)]]
[[Node: IteratorGetNext = IteratorGetNextoutput_shapes=[[?,?], [?,?], [?,?], [?], [?]], output_types=[DT_INT32, DT_INT32, DT_INT32, DT_INT32, DT_INT32], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]
can anyone please help me with this. Im I doing any wrong? i reduced the batch size to 2 and also the units to 800. I was able to train with your own data before , but when i tried it for my own data along with some of your data it shows this.
the vocab generator python file shows this result: Vocab size after all base data files scanned: 256 Vocab size after cornell data file scanned: 18354 The final vocab file generated. Vocab size: 18380 Please can anyone help me with this.