InvalidArgumentError: Assign requires shapes of both tensors to match , #2

[abhishekgupte94]

Hi.
I've already trained a seq2seq model following this brilliant article, however I would like to train it more on new data and would seriously love to avoid training the whole thing again instead. I keep getting this InvalidArgumentError: Assign requires shapes of both tensors to match." error whenever I restore the model and try to retrain it using the normal way of training a model. Any ideas on how to go about this?

[adeshpande3]

#9 Double check to make sure that the shapes of all your variables are the same as the graph you saved, same number of LSTM units, etc.