Skip to content

Support in_channels in image-text-to-text #205

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

Merged
sdpython merged 1 commit into from
Aug 27, 2025
Merged

Support in_channels in image-text-to-text #205

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
6 changes: 4 additions & 2 deletions onnx_diagnostic/tasks/image_text_to_text.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,7 +348,7 @@ def random_input_kwargs(config: Any) -> Tuple[Dict[str, Any], Callable]:
"vision_config",
)
text_config = False
check_hasattr(config.vision_config, ("num_channels", "in_chans"))
check_hasattr(config.vision_config, ("num_channels", "in_chans", "in_channels"))
kwargs = dict(
batch_size=2,
sequence_length=43,
Expand Down Expand Up @@ -421,7 +421,9 @@ def random_input_kwargs(config: Any) -> Tuple[Dict[str, Any], Callable]:
else config.vision_config.image_size
),
num_channels=(
3 if config is None else _pick(config.vision_config, "num_channels", "in_chans")
3
if config is None
else _pick(config.vision_config, "num_channels", "in_chans", "in_channels")
),
pad_token_id=(
0
Expand Down
Loading