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

fixed imports + readme.md

This commit is contained in:
andrea 2021-01-26 16:20:51 +01:00
parent bcc22fe44a
commit c769f59d5a
1 changed files with 11 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
readme.md
View File

@ -11,30 +11,18 @@ positional arguments:
optional arguments: optional arguments:
-h, --help show this help message and exit -h, --help show this help message and exit
-o CSV_DIR, --output CSV_DIR -o, --output Result file (default ../csv_logs/gfun/gfun_results.csv)
Result file (default ../csv_logs/gfun/gfun_results.csv) -x, --post_embedder deploy posterior probabilities embedder to compute document embeddings
-x, --post_embedder deploy posterior probabilities embedder to compute -w, --wce_embedder deploy (supervised) Word-Class embedder to the compute document embeddings
document embeddings -m, --muse_embedder deploy (pretrained) MUSE embedder to compute document embeddings
-w, --wce_embedder deploy (supervised) Word-Class embedder to the compute -b, --bert_embedder deploy multilingual Bert to compute document embeddings
document embeddings
-m, --muse_embedder deploy (pretrained) MUSE embedder to compute document
embeddings
-b, --bert_embedder deploy multilingual Bert to compute document
embeddings
-g, --gru_embedder deploy a GRU in order to compute document embeddings -g, --gru_embedder deploy a GRU in order to compute document embeddings
-c, --c_optimize Optimize SVMs C hyperparameter -c, --c_optimize Optimize SVMs C hyperparameter
-n NEPOCHS, --nepochs NEPOCHS -n, --nepochs Number of max epochs to train Recurrent embedder (i.e., -g)
Number of max epochs to train Recurrent embedder -j, --n_jobs Number of parallel jobs (default is -1, all)
(i.e., -g) --muse_dir MUSE_DIR Path to the MUSE polylingual word embeddings (default ../embeddings)
-j N_JOBS, --n_jobs N_JOBS --gru_wce Deploy WCE embedding as embedding layer of the GRU View Generator
Number of parallel jobs (default is -1, all) --gru_dir GRU_DIR Set the path to a pretrained GRU model (i.e., -g view generator)
--muse_dir MUSE_DIR Path to the MUSE polylingual word embeddings (default --bert_dir BERT_DIR Set the path to a pretrained mBERT model (i.e., -b view generator)
../embeddings)
--gru_wce Deploy WCE embedding as embedding layer of the GRU
View Generator
--gru_dir GRU_DIR Set the path to a pretrained GRU model (i.e., -g view
generator)
--bert_dir BERT_DIR Set the path to a pretrained mBERT model (i.e., -b
view generator)
--gpus GPUS specifies how many GPUs to use per node --gpus GPUS specifies how many GPUs to use per node
``` ```