You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
Hello Patrick, on my end, I went into the utils.py(line 218) file and changed expected_args = inspect.getargspec(optim_fn.init)[0] into expected_args = inspect.getfullargspec(optim_fn.__init__)[0]. After that, it went fine.
Hello Patrick, on my end, I went into the utils.py(line 218) file and changed expected_args = inspect.getargspec(optim_fn.init)[0] into expected_args = inspect.getfullargspec(optim_fn.__init__)[0]. After that, it went fine.
I'm running into issues when trying to execute the unsupervised alignement (Python 3.8.16) :
python MUSE-main/unsupervised.py --src_lang en --tgt_lang fr --src_emb corpus_en.tag.bin --tgt_emb corpus_fr.tag.bin --n_refinement 5 --emb_dim 100
INFO - 01/29/23 17:30:10 - 0:00:00 - ============ Initialized logger ============
INFO - 01/29/23 17:30:10 - 0:00:00 - adversarial: True
batch_size: 32
cuda: True
dico_build: S2T
dico_eval: default
dico_max_rank: 15000
dico_max_size: 0
dico_method: csls_knn_10
dico_min_size: 0
dico_threshold: 0
dis_clip_weights: 0
dis_dropout: 0.0
dis_hid_dim: 2048
dis_input_dropout: 0.1
dis_lambda: 1
dis_layers: 2
dis_most_frequent: 75000
dis_optimizer: sgd,lr=0.1
dis_smooth: 0.1
dis_steps: 5
emb_dim: 100
epoch_size: 1000000
exp_id:
exp_name: debug
exp_path: /part/02/data/me/metavirt/MUSE-main/dumped/debug/1gyrk6dihw
export: txt
lr_decay: 0.98
lr_shrink: 0.5
map_beta: 0.001
map_id_init: True
map_optimizer: sgd,lr=0.1
max_vocab: 200000
min_lr: 1e-06
n_epochs: 5
n_refinement: 5
normalize_embeddings:
seed: -1
src_emb: corpus_en.tag.bin
src_lang: en
tgt_emb: corpus_fr.tag.bin
tgt_lang: fr
verbose: 2
INFO - 01/29/23 17:30:10 - 0:00:00 - The experiment will be stored in /part/02/data/me/metavirt/MUSE-main/dumped/debug/1gyrk6dihw
INFO - 01/29/23 17:30:11 - 0:00:01 - Loaded binary model. Generating embeddings ...
INFO - 01/29/23 17:30:13 - 0:00:02 - Generated embeddings for 39391 words.
INFO - 01/29/23 17:30:14 - 0:00:03 - Loaded binary model. Generating embeddings ...
INFO - 01/29/23 17:30:16 - 0:00:06 - Generated embeddings for 56481 words.
Traceback (most recent call last):
File "MUSE-main/unsupervised.py", line 96, in
trainer = Trainer(src_emb, tgt_emb, mapping, discriminator, params)
File "/part/02/data/me/metavirt/MUSE-main/src/trainer.py", line 41, in init
optim_fn, optim_params = get_optimizer(params.map_optimizer)
File "/part/02/data/me/metavirt/MUSE-main/src/utils.py", line 218, in get_optimizer
expected_args = inspect.getargspec(optim_fn.init)[0]
File "/usr/lib/python3.8/inspect.py", line 1095, in getargspec
raise ValueError("Function has keyword-only parameters or annotations"
ValueError: Function has keyword-only parameters or annotations, use inspect.signature() API which can support them
Any ideas or suggestions to fix this?
The text was updated successfully, but these errors were encountered: