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

readme.md

This commit is contained in:
andrea 2021-01-26 17:23:54 +01:00
parent ffd870b4b4
commit 1a501949a1
2 changed files with 20 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
main.py
View File

@ -42,11 +42,11 @@ def main(args):
if args.gru_embedder:
rnnEmbedder = RecurrentGen(multilingualIndex, pretrained_embeddings=lMuse, wce=args.gru_wce, batch_size=256,
nepochs=args.nepochs, gpus=args.gpus, n_jobs=args.n_jobs)
nepochs=args.nepochs_rnn, gpus=args.gpus, n_jobs=args.n_jobs)
embedder_list.append(rnnEmbedder)
if args.bert_embedder:
bertEmbedder = BertGen(multilingualIndex, batch_size=4, nepochs=10, gpus=args.gpus, n_jobs=args.n_jobs)
bertEmbedder = BertGen(multilingualIndex, batch_size=4, nepochs=args.nepochs_bert, gpus=args.gpus, n_jobs=args.n_jobs)
embedder_list.append(bertEmbedder)
# Init DocEmbedderList (i.e., first-tier learners or view generators) and metaclassifier
@ -136,13 +136,18 @@ if __name__ == '__main__':
help='Optimize SVMs C hyperparameter',
default=False)
parser.add_argument('-n', '--nepochs', dest='nepochs', type=int,
help='Number of max epochs to train Recurrent embedder (i.e., -g)')
parser.add_argument('-j', '--n_jobs', dest='n_jobs', type=int,
help='Number of parallel jobs (default is -1, all)',
default=-1)
parser.add_argument('--nepochs_rnn', dest='nepochs_rnn', type=int,
help='Number of max epochs to train Recurrent embedder (i.e., -g), default 150.',
default=150)
parser.add_argument('--nepochs_bert', dest='nepochs_bert', type=int,
help='Number of max epochs to train Bert model (i.e., -g), default 10',
default=10)
parser.add_argument('--muse_dir', dest='muse_dir', type=str,
help='Path to the MUSE polylingual word embeddings (default ../embeddings)',
default='../embeddings')

19
readme.md
View File

@ -30,18 +30,19 @@ positional arguments:
optional arguments:
-h, --help show this help message and exit
-o, --output Result file (default ../csv_logs/gfun/gfun_results.csv)
-o, --output result file (default ../csv_logs/gfun/gfun_results.csv)
-x, --post_embedder deploy posterior probabilities embedder to compute document embeddings
-w, --wce_embedder deploy (supervised) Word-Class embedder to the compute 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
-c, --c_optimize Optimize SVMs C hyperparameter
-n, --nepochs Number of max epochs to train Recurrent embedder (i.e., -g)
-j, --n_jobs Number of parallel jobs (default is -1, all)
--muse_dir 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_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
-c, --c_optimize optimize SVMs C hyperparameter
-j, --n_jobs number of parallel jobs (default is -1, all)
--nepochs_rnn number of max epochs to train Recurrent embedder (i.e., -g), default 150.
--nepochs_bert number of max epochs to train Bert model (i.e., -g), default 10
--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_dir set the path to a pretrained GRU model (i.e., -g 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
```