Calculate NMS
Having extracted the predicted bounding boxes and scores from your object recognition model, your next task is to ensure that only the most accurate and non-overlapping predicted bounding boxes are retained by using the non-max suppression technique.
boxes and scores you created in the previous exercise are available in your workspace and torch and torchvision have been imported.
Questo esercizio fa parte del corso
Deep Learning for Images with PyTorch
Istruzioni dell'esercizio
- Import
nmsfromtorchvision.ops. - Set the IoU threshold to be equal
0.5. - Apply non-max suppression passing
boxes,confidence_scores, andiou_thresholdto the relevant function. - Use the output indices to filter predicted boxes.
Esercizio pratico interattivo
Prova a risolvere questo esercizio completando il codice di esempio.
# Import nms
____
# Set the IoU threshold
iou_threshold = ____
# Apply non-max suppression
box_indices = ____
# Filter boxes
filtered_boxes = ____
print("Filtered Boxes:", filtered_boxes)