加载图像

import cv2

image = cv2.imread("...")

创建和优化标记

import maestro

generator = maestro.SegmentAnythingMarkGenerator(device='cuda')
marks = generator.generate(image=image)
marks = maestro.refine_marks(marks=marks)

可视化标记

mark_visualizer = maestro.MarkVisualizer()
marked_image = mark_visualizer.visualize(image=image, marks=marks)

提示

prompt = "找到狗。"

response = maestro.prompt_image(api_key=api_key, image=marked_image, prompt=prompt)

>>> "狗在图像中央显著位置，标记为[9]。"

提取相关标记

masks = maestro.extract_relevant_masks(text=response, detections=refined_marks)

>>> {'6': array([
...     [False, False, False, ..., False, False, False],
...     [False, False, False, ..., False, False, False],
...     [False, False, False, ..., False, False, False],
...     ...,
...     [ True,  True,  True, ..., False, False, False],
...     [ True,  True,  True, ..., False, False, False],
...     [ True,  True,  True, ..., False, False, False]])
... }