Skip to content
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.

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

VQA: add option for beam-search validation during fine-tuning #79

Merged
merged 6 commits into from
Apr 24, 2022
Merged
Changes from 1 commit
Commits
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
Prev Previous commit
Next Next commit
VQA: add option for beam-search validation during fine-tuning
  • Loading branch information
yangapku committed Apr 22, 2022
commit 3c1258b52937cdc2afc16df7c78e19c8a0486f14
2 changes: 1 addition & 1 deletion tasks/mm_tasks/vqa_gen.py
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,7 @@ class VqaGenConfig(OFAConfig):
metadata={"help": "inference type in validation (allcand or beamsearch), default to allcand"},
)
eval_args: Optional[str] = field(
default='{"beam":5,"unnormalized":True,"temperature":1.0}',
default='{"beam":5,"unnormalized":true,"temperature":1.0}',
metadata={
"help": 'generation args as JSON string for inference, only activated when --val-inference-type=beamsearch'
},
Expand Down