Skip to content

Improvements to Null Checks and Device Assignment in LSI and ETM Models #126

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Improvements to Null Checks and Device Assignment in LSI and ETM Models #126

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1f2d45a
fix_none_check_and_device_assignment
XavierSpycy Jun 14, 2024
25293e5
fix_none_check_and_device_assignment
XavierSpycy Jun 15, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 7 additions & 4 deletions octis/models/ETM.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ def __init__(
self, num_topics=10, num_epochs=100, t_hidden_size=800, rho_size=300,
embedding_size=300, activation='relu', dropout=0.5, lr=0.005,
optimizer='adam', batch_size=128, clip=0.0, wdecay=1.2e-6, bow_norm=1,
device='cpu', train_embeddings=True, embeddings_path=None,
device='cuda', train_embeddings=True, embeddings_path=None,
embeddings_type='pickle', binary_embeddings=True,
headerless_embeddings=False, use_partitions=True):
"""
Expand Down Expand Up @@ -131,9 +131,12 @@ def set_model(self, dataset, hyperparameters):
self.train_tokens, self.train_counts = self.preprocess(
vocab2id, data_corpus, None)

self.device = torch.device(
"cuda" if torch.cuda.is_available() else "cpu")

if isinstance(self.device, str):
self.device = torch.device(self.device)

if (self.device.type == 'cuda' and not torch.cuda.is_available()) or (self.device.type == 'mps' and not torch.backends.mps.is_available()):
self.device = torch.device('cpu')

self.set_default_hyperparameters(hyperparameters)
self.load_embeddings()
# define model and optimizer
Expand Down
4 changes: 2 additions & 2 deletions octis/models/LSI.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,10 +106,10 @@ def train_model(self, dataset, hyperparameters={}, top_words=10):
else:
partition = [dataset.get_corpus(), []]

if self.id2word == None:
if self.id2word is None:
self.id2word = corpora.Dictionary(dataset.get_corpus())

if self.id_corpus == None:
if self.id_corpus is None:
self.id_corpus = [self.id2word.doc2bow(
document) for document in partition[0]]

Expand Down