search

lvapeab / nmt-keras

Neural Machine Translation with Keras
http://nmt-keras.readthedocs.io
MIT License
532 stars 130 forks source link

Training Error #141

Open RajarshiBhadra opened 3 years ago

RajarshiBhadra commented 3 years ago

I am facing an issue while trying to train a model as follows

`Epoch 1/4

InvalidArgumentError Traceback (most recent call last) /usr/local/lib/python3.7/dist-packages/tensorflow_core/python/client/session.py in _do_call(self, fn, args) 1364 try: -> 1365 return fn(args) 1366 except errors.OpError as e:

14 frames /usr/local/lib/python3.7/dist-packages/tensorflow_core/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata) 1349 return self._call_tf_sessionrun(options, feed_dict, fetch_list, -> 1350 target_list, run_metadata) 1351

/usr/local/lib/python3.7/dist-packages/tensorflow_core/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata) 1442 fetch_list, target_list, -> 1443 run_metadata) 1444

InvalidArgumentError: Incompatible shapes: [50,16] vs. [50,15] [[{{node loss/target_text_loss/mul}}]]`

I understand 50 is the batch size I am giving but the 16 or 15 are not parameters I am providing. Any Idea what might be causing this error?

lvapeab commented 3 years ago

Hi, it seems an output vocabulary dimension issue. Were you able to run the examples? Can you post the config file you are using?

Thanks