Tweeted By @chipro

By breaking the training of sequence-to-sequence models into 5 steps (encoding, decoding, attending, predicting, search), SEQ2SEQ-VIS visualizes training and possible errors at each step. It'd be great to have this built-in with TensorFlow / PyTorch https://t.co/PJFlrNoAKv

— Chip Huyen (@chipro) October 18, 2018