袁宵
For beginners, the original method seems too complicated. In fact, it only needs simple tensor slicing operation to achieve the same effect.
Should increase the logical judgment of using pre-trained Glove word vectors. Otherwise, when "use_pretrained = False"(config.py), running build_data.py directly will report an error(No such file or directory: 'data/glove.6B/glove.6B.300d.txt').
I need you help! I converted your dlnd_language_translation v2.ipynb into seq2seq_RNN_model_batch_size.py. On the verification set, the effect of the model is much worse than yours. seq2seq_RNN_model.py I also wrote a...
