andrea.pedrotti
/
gFun
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Set arguments in order to reproduce 'master' performances with Neural setting

This commit is contained in:
andrea 2021-01-29 18:20:29 +01:00
parent b3275667bb
commit a301afde97
1 changed files with 0 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
readme.md
View File

@ -46,7 +46,6 @@ optional arguments:
--batch_bert set batchsize for the BertGen, default 4 --batch_bert set batchsize for the BertGen, default 4
--muse_dir path to the MUSE polylingual word embeddings (default ../embeddings) --muse_dir path to the MUSE polylingual word embeddings (default ../embeddings)
--gru_wce deploy WCE embedding as embedding layer of the GRU View Generator --gru_wce deploy WCE embedding as embedding layer of the GRU View Generator
--patience_rnn set early stop patience for the RecurrentGen, default 50
--rnn_dir set the path to a pretrained RNN model (i.e., -g view generator) --rnn_dir set the path to a pretrained RNN model (i.e., -g view generator)
--bert_dir set the path to a pretrained mBERT model (i.e., -b view generator) --bert_dir set the path to a pretrained mBERT model (i.e., -b view generator)
--gpus specifies how many GPUs to use per node --gpus specifies how many GPUs to use per node