nslt

nslt copied to clipboard

Another error during training (python 2.7)

5

Here is the command I run: `python -m nmt --src=sign --tgt=de --train_prefix=../Data/phoenix2014T.train --dev_prefix=../Data/phoenix2014T.dev --test_prefix=../Data/phoenix2014T.test --out_dir=../test_out/ --vocab_prefix=../Data/phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=0 --unit_type=gru` Here is the error I get,...

vbelissen

BestModel download link not working

1

The DropBox link to download the file under the BestModel directory is no longer working. @neccam Could you please update the link?

hshreeshail

Excuse me,I am a newer of this field. About this network architecture, Can I want to use it from English signs to English? or it is only used from German...

zhouhuiwang

Pre-trained model

4

Hi, Thanks for the great work! Would it please be possible to share a trained model that we can run evaluation on? I do not have the resources to train...

sxs4337

Missing hparams file in Best Model

1

Hi, I'm trying to use the best model which is downloaded from the dropbox link. I'm trying to do inference only without any training. After downloading and unzipping the files,...

tongyao-zhu

Hi all, I am trying to reproduce the result this repo and also newer repo here: https://github.com/neccam/slt I just wonder how data pre-processed ? when I download from 1): https://www-i6.informatik.rwth-aachen.de/~koller/RWTH-PHOENIX-2014-T/...

STAROFWIND

while training the model using this command: python -m nmt --src=gloss --tgt=de --train_prefix=../Data/phoenix2014T.train --dev_prefix=../Data/phoenix2014T.dev --test_prefix=../Data/phoenix2014T.test --out_dir=/home/ml2/nslt-master/nslt/model --vocab_prefix=../Data/phoenix2014T.vocab --source_reverse=True --num_units=1000 --num_layers=4 --num_train_steps=150000 --residual=True --attention=luong --base_gpu=0 --unit_type=gru The error below was raised....

NouranAbdelaziz

Thank you for your contribution! I just changed the images in the dataset. Put the sign language's picture into openpose to get the skeleton map, and the file name remains...

zhang197

Error "UnicodeEncodeError: 'ascii' codec can't encode character u'\xe4' "

1

When I try to execute the code always come this error: ``` dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/kernel:0, (2000, 2000), /device:GPU:1 dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/gates/bias:0, (2000,), /device:GPU:1 dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/kernel:0, (2000, 1000), /device:GPU:1 dynamic_seq2seq/decoder/attention/multi_rnn_cell/cell_3/gru_cell/candidate/bias:0, (1000,), /device:GPU:1 dynamic_seq2seq/decoder/attention/attention_layer/kernel:0, (2000, 1000), /device:GPU:1...

kyumiouchi

Awesome repo . For our college project i am using this can you share the images after resizing also (like drive link ).

LeelaPrasad-LP