search

leitro / attentionMNISTseq2seq

Use encoder-decoder with Bahdanau attention to predict MNIST digits sequence
7 stars 6 forks source link

images #1

Open leitro opened 6 years ago

leitro commented 6 years ago

screenshot from 2017-10-23 12-13-38 Figure 1. Encoder-decoder model with Bahdanau attention

screenshot from 2017-11-02 11-00-57 Figure 2. Generated digits sequence based on MNIST

screenshot from 2017-11-02 11-15-53 Figure 3. CER and LOSS of basic encoder-decoder model

screenshot from 2017-11-02 11-17-09 Figure 4. CER and LOSS of encoder-decoder model with Bahdanau attention

screenshot from 2017-11-02 11-18-06 Figure 5. CER and LOSS of encoder-decoder model with Bahdanau attention using self-predicted value as decoder input