Skip to content

fix winclip openvino inference output without mask #2083

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

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

fix winclip openvino inference output without mask #2083

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
a9a7cd5
fix winclip openvino inference output without mask
junxnone May 24, 2024
7ce79a6
Revert "fix for winclip openvino inference without mask"
junxnone May 30, 2024
b63cb5f
fix openvino inferencer results parser
junxnone May 30, 2024
52e5364
fix format
junxnone May 31, 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
17 changes: 10 additions & 7 deletions src/anomalib/deploy/inferencers/openvino_inferencer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,7 +147,7 @@ def load_model(self, path: str | Path | tuple[bytes, bytes]) -> tuple[Any, Any,
compile_model = core.compile_model(model=model, device_name=self.device, config=self.config)

input_blob = compile_model.input(0)
output_blob = compile_model.output(0)
output_blob = compile_model.outputs

return input_blob, output_blob, compile_model

Expand Down Expand Up @@ -254,7 +254,7 @@ def post_process(self, predictions: np.ndarray, metadata: dict | DictConfig | No
if metadata is None:
metadata = self.metadata

predictions = predictions[self.output_blob]
predictions = [predictions[i] for i in self.output_blob]

# Initialize the result variables.
anomaly_map: np.ndarray | None = None
Expand All @@ -263,13 +263,16 @@ def post_process(self, predictions: np.ndarray, metadata: dict | DictConfig | No

# If predictions returns a single value, this means that the task is
# classification, and the value is the classification prediction score.
if len(predictions.shape) == 1:
if len(predictions) == 1:
task = TaskType.CLASSIFICATION
pred_score = predictions
pred_score = predictions[0]
else:
task = TaskType.SEGMENTATION
anomaly_map = predictions.squeeze()
pred_score = anomaly_map.reshape(-1).max()
task = TaskType.SEGMENTATION if self.task is None else self.task
for item in predictions:
if len(item.shape) == 1:
pred_score = item[0]
else:
anomaly_map = item.squeeze()

# Common practice in anomaly detection is to assign anomalous
# label to the prediction if the prediction score is greater
Expand Down