liperrino

Hi. This is a wonderfull work. Please can you guide me so that i can achieve the same thing with transfomer?

Hi. Please, i would like to do attention weight visualization on transformer like you did here. Please can you help me

TypeError: tuple indices must be integers or slices, not tuple when translating

1

I have this error: TypeError: tuple indices must be integers or slices, not tuple, when try this: python translate.py -data_pkl m30k_deen_shr.pkl -model trained.chkpt -output prediction.txt

Attention weight plot

3

Please, how to add Attention weight plot to this code. Thanks in advance

How do we use scripts under the train folder

1

Hi. Please i would like to know how to train train these models. When i ran train_en_de.sh, i get errors: Traceback (most recent call last): File "/media/vivien/A/NEW-SMT/seq2seq.pytorch-master/main.py", line 15, in...

How to add some functionalities to this code?

1

Hi. Please i would like to add some features to this code that i have read on beam search. Like coverage penalty and length normalization. But i don't know where...

TypeError: on __init()__ missing require positional argument: out_features

3

python3 train.py -model_path models -data_path models/preprocess-train.t7 Namespace(batch_size=128, d_ff=2048, d_k=64, d_model=512, d_v=64, data_path='models/preprocess-train.t7', display_freq=100, dropout=0.1, log=None, lr=0.0002, max_epochs=10, max_grad_norm=None, max_src_seq_len=50, max_tgt_seq_len=50, model_path='models', n_heads=8, n_layers=6, n_warmup_steps=4000, share_embs_weight=False, share_proj_weight=False, weighted_model=False) Loading training and...

Please i would like to know how to use this repository because i am getting errors that i don't understand will running it.

Traceback (most recent call last): File "train.py", line 90, in train() File "train.py", line 81, in train writer.export_scalars_to_json(hp.model_dir + '/all_scalars.json') AttributeError: 'SummaryWriter' object has no attribute 'export_scalars_to_json' How can i...

Hi. Please i would like to add some features to this code that i have read on beam search. Like coverage penalty and length normalization. But i don't know where...