Skip to content

Fix image detection inference viz in gui #611

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
dpascualhe merged 2 commits into from
Jul 2, 2026
Merged

Fix image detection inference viz in gui #611

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
18906da
Fix image detection inference viz in gui
dpascualhe Jul 2, 2026
de5a8e8
Remove unused variables
dpascualhe Jul 2, 2026
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
2 changes: 1 addition & 1 deletion perceptionmetrics/models/torch_detection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,7 +270,7 @@ class DetectionModelWrapper(torch.nn.Module):
def __init__(self, model):
super().__init__()
self.inner_model = model

# Handle input precision, tuple extraction, and output precision
def forward(self, x):
out = self.inner_model(x)
Expand Down
10 changes: 3 additions & 7 deletions tabs/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,19 +74,15 @@ def inference_tab():
with st.spinner("Running inference..."):
try:
image = Image.open(image_file).convert("RGB")
predictions, sample_tensor = st.session_state.detection_model.predict(
image, return_sample=True
)
from torchvision.transforms import v2 as transforms
predictions = st.session_state.detection_model.predict(image)

img_to_draw = transforms.ToPILImage()(sample_tensor[0])
label_map = getattr(
st.session_state.detection_model, "idx_to_class_name", None
)
result_img = draw_detections(img_to_draw, predictions, label_map)
result_img = draw_detections(image, predictions, label_map)

st.markdown("#### Detection Results")
st.image(result_img, caption="Detection Results", width="stretch")
st.image(result_img, caption="Detection Results", width="content")

# Display detection statistics
if (
Expand Down
Loading