Skip to content

Fix pytorch sentiment device arg #38143

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

Closed
aIbrahiim wants to merge 1 commit into from
Closed

Fix pytorch sentiment device arg #38143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 0 additions & 1 deletion ...erence_Python_Benchmarks_Dataflow_Pytorch_Sentiment_Streaming_DistilBert_Base_Uncased.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,5 @@
--device=CPU
--input_file=gs://apache-beam-ml/testing/inputs/sentences_50k.txt
--runner=DataflowRunner
--dataflow_service_options=worker_accelerator=type:nvidia-tesla-t4;count:1;install-nvidia-driver
--model_path=distilbert-base-uncased-finetuned-sst-2-english
--model_state_dict_path=gs://apache-beam-ml/models/huggingface.sentiment.distilbert-base-uncased.pth
15 changes: 11 additions & 4 deletions sdks/python/apache_beam/examples/inference/pytorch_sentiment.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,7 +98,11 @@ def parse_known_args(argv):
required=True,
help="Path to the model's state_dict.")
parser.add_argument(
'--input', required=True, help='Path to input file on GCS')
'--input',
'--input_file',
dest='input',
required=True,
help='Path to input file on GCS (load tests pass --input_file).')
parser.add_argument(
'--pubsub_topic',
default='projects/apache-beam-testing/topics/test_sentiment_topic',
Expand All @@ -117,6 +121,11 @@ def parse_known_args(argv):
type=float,
default=None,
help='Elements per second to send to Pub/Sub')
parser.add_argument(
'--device',
default='CPU',
choices=['CPU', 'GPU'],
help='Device to use for inference. Choices are CPU or GPU.')
return parser.parse_known_args(argv)


Expand Down Expand Up @@ -183,8 +192,6 @@ def override_or_add(args, flag, value):

def run_load_pipeline(known_args, pipeline_args):
"""Load data pipeline: read lines from GCS file and send to Pub/Sub."""

override_or_add(pipeline_args, '--device', 'CPU')
override_or_add(pipeline_args, '--num_workers', '5')
override_or_add(pipeline_args, '--max_num_workers', '10')
override_or_add(
Expand Down Expand Up @@ -238,7 +245,7 @@ def run(
model_class=DistilBertForSequenceClassification,
model_params={'config': DistilBertConfig(num_labels=2)},
state_dict_path=known_args.model_state_dict_path,
device='GPU')
device=known_args.device)

tokenizer = DistilBertTokenizerFast.from_pretrained(known_args.model_path)

Expand Down
Loading