tygrer
commented
5 years ago This is my dataset issue. I resovled by clean the dirty data.
Closed tygrer closed 5 years ago
tygrer
commented
5 years ago This is my dataset issue. I resovled by clean the dirty data.
Does someone meet this issue before? I tried to retrain the model by sovling the chinese character recognition. And I used the number to replace the character, and splite by '$'. But when I run the train.py script, here the issue showed. INFO:tensorflow:Error reported to Coordinator: <class 'tensorflow.python.framework.errors_impl.InvalidArgumentError'>, pos 0 out of range for stringb'' at index 0 [[Node: Input/case_1/If_0/decode_image/Substr = Substr[T=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Input/case_1/If_0/decode_image/Substr/Switch:1, Input/case_1/If_0/decode_image/Substr/pos, Input/case_1/If_0/decode_image/Substr/len)]] INFO:tensorflow:Saving checkpoints for 68 into /home/tanggy/aster/experiments/demo/log/model.ckpt. Traceback (most recent call last): File "aster/train.py", line 216, in
tf.app.run()
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "aster/train.py", line 212, in main
worker_job_name, is_chief, train_dir)
File "/home/tanggy/aster/trainer.py", line 268, in train
config=session_config
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/contrib/training/python/training/training.py", line 538, in train
loss = session.run(train_op)
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 537, in exit
self._close_internal(exception_type)
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 574, in _close_internal
self._sess.close()
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 820, in close
self._sess.close()
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/monitored_session.py", line 941, in close
ignore_live_threads=True)
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/coordinator.py", line 389, in join
six.reraise(*self._exc_info_to_raise)
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/six.py", line 685, in reraise
raise value.with_traceback(tb)
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/queue_runner_impl.py", line 238, in _run
enqueue_callable()
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1231, in _single_operation_run
target_list_as_strings, status, None)
File "/home/tanggy/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: pos 0 out of range for stringb'' at index 0
[[Node: Input/case_1/If_0/decode_image/Substr = Substr[T=DT_INT32, _device="/job:localhost/replica:0/task:0/device:CPU:0"](Input/case_1/If_0/decode_image/Substr/Switch:1, Input/case_1/If_0/decode_image/Substr/pos, Input/case_1/If_0/decode_image/Substr/len)]]