utils/fastSAM.py

def FastSAM_points_inference(
    input,
    input_size=1024, 
    iou_threshold=0.7,
    conf_threshold=0.25,
    better_quality=False,
    withContours=True,
    use_retina=True,
    mask_random_color=True,
):
    global global_points
    global global_point_label
    input = Image.fromarray(input)
    input_size = int(input_size)  # 确保 imgsz 是整数
    # Thanks for the suggestion by hysts in HuggingFace.
    w, h = input.size
    scale = input_size / max(w, h)
    new_w = int(w * scale)
    new_h = int(h * scale)
    input = input.resize((new_w, new_h))
    
    scaled_points = [[int(x * scale) for x in point] for point in global_points]

    results = FASTSAM_MODEL(input,
                    device=DEVICE,
                    retina_masks=True,
                    iou=iou_threshold,
                    conf=conf_threshold,
                    imgsz=input_size,)
    
    results = format_results(results[0], 0)
    annotations, _ = point_prompt(results, scaled_points, global_point_label, new_h, new_w)
    annotations = np.array([annotations])

    fig = fast_process(annotations=annotations,
                       image=input,
                       device=DEVICE,
                       scale=(1024 // input_size),
                       better_quality=better_quality,
                       mask_random_color=mask_random_color,
                       bbox=None,
                       use_retina=use_retina,
                       withContours=withContours,)
    
    global_points = []
    global_point_label = []
    
    return fig