set memory_optimize=False, can't dectect anything

[LudovicoYIN]

When i set memory_optimize=False, i can't dectect anything

[Koldim2001]

@LudovicoYIN
When using the memory_optimize=False mode, the results of masks will be stored as an array of binary masks result.filtered_masks for each object (insted of list of plygons as in memory_optimize=True example).

img=result.image
confidences=result.filtered_confidences
boxes=result.filtered_boxes
masks=result.filtered_masks
classes_ids=result.filtered_classes_id
classes_names=result.filtered_classes_names

Here's an example of how to visualize the results in such case:

element_crops = MakeCropsDetectThem(
    image=img,
    model_path="yolov9e-seg.pt",
    segment=True,
    show_crops=True,
    shape_x=350,
    shape_y=250,
    overlap_x=50,
    overlap_y=50,
    conf=0.5,
    iou=0.7,
    imgsz=416,
    classes_list=[0, 1, 2, 3, 5, 7],
    resize_initial_size=True,
    memory_optimize=False
)
result = CombineDetections(element_crops, nms_threshold=0.5, match_metric='IOS')

print('YOLO-Patch-Based-Inference:')
visualize_results(
    img=result.image,
    confidences=result.filtered_confidences,
    boxes=result.filtered_boxes,
    masks=result.filtered_masks,
    classes_ids=result.filtered_classes_id,
    classes_names=result.filtered_classes_names,
    segment=True,
    thickness=6,
    font_scale=1.1,
    fill_mask=True,
    show_boxes=False,
    delta_colors=3,
    show_class=False,
    axis_off=False
)

More exaples - Colab

[Koldim2001]

@LudovicoYIN How are your results? Did using filtered_masks instead of filtered_polygons help you solve the problem?

[LudovicoYIN]

Thank you so much Sir, i forget add masks=result.filtered_masks, i still use filtered_polygons