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.

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

Jump to bottom

Limit number of frames sent to reflection #64

Merged
merged 4 commits into from
Apr 25, 2024
Merged

Limit number of frames sent to reflection #64

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
7fb2a80
add sample for frames
dillonalaird Apr 24, 2024
adad87a
add test cases
dillonalaird Apr 24, 2024
5e3c8cd
updated function'
dillonalaird Apr 25, 2024
3601d86
black and isort
dillonalaird Apr 25, 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
15 changes: 14 additions & 1 deletion vision_agent/agent/vision_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -366,6 +366,19 @@ def _handle_viz_tools(
return image_to_data


def sample_n_evenly_spaced(lst: Sequence, n: int) -> Sequence:
shankar-vision-eng marked this conversation as resolved.
Show resolved Hide resolved
if n <= 0:
return []

if len(lst) <= n:
return lst

interval = len(lst) // n if len(lst) % 2 == 0 else len(lst) // n + 1
indices = list(range(len(lst)))
picked_indices = sorted([indices[(i * interval) % len(lst)] for i in range(n)])
return [lst[i] for i in picked_indices]


dillonalaird marked this conversation as resolved.
Show resolved Hide resolved
def visualize_result(all_tool_results: List[Dict]) -> Sequence[Union[str, Path]]:
image_to_data: Dict[str, Dict] = {}
for tool_result in all_tool_results:
Expand Down Expand Up @@ -584,7 +597,7 @@ def chat_with_workflow(
visualized_output = visualize_result(all_tool_results)
all_tool_results.append({"visualized_output": visualized_output})
if len(visualized_output) > 0:
reflection_images = visualized_output
reflection_images = sample_n_evenly_spaced(visualized_output, 3)
elif image is not None:
reflection_images = [image]
else:
Expand Down
Loading