liperrino

> you can get attention weight by this code below, > > ``` > model.(enc|dec)oder.forward([target sequences], return_attns=True) > ``` > > and then, as you know, can visualize attention weight...

> you can get attention weight by this code below, > > ``` > model.(enc|dec)oder.forward([target sequences], return_attns=True) > ``` > > and then, as you know, can visualize attention weight...

> Hi. Please i would like to know how to add a new layer in your Transformer model between the Encoder and Decoder Layers so that the outputs coming from...

I have the same error when running: python3 train.py -i data/de_en --data demo --wbatchsize 4096 --batchsize 60 --tied --beam_size 5 --epoch 40 --layers 6 --multi_heads 8 The error is, RuntimeError:...

> After preprocessing the data, when running the following command (no gpu): > > python train.py -i data/ja_en --data demo --wbatchsize 4096 --batchsize 60 --tied --beam_size 5 --epoch 5 --layers...