点击上方“小白学视觉”，选择加"星标"或“置顶”
重磅干货，第一时间送达
# Install Generative AI SDK.!pip install -q -U google-generativeai# Import librariesfrom google.colab import userdataimport google.generativeai as genaiimport refrom PIL import Imageimport cv2import numpy as np
API_KEY = userdata.get('gemini')genai.configure(api_key=API_KEY)model = genai.GenerativeModel(model_name='gemini-1.5-pro')
input_image = "image.jpg" # @param {type : 'string'}img = Image.open(input_image)response = model.generate_content([img,("Return bounding boxes for all objects in the image in the following format as"" a list. \n [ymin, xmin, ymax, xmax, object_name]. If there are more than one object, return separate lists for each object"),])result = response.text
def parse_bounding_box(response):bounding_boxes = re.findall(r'\[(\d+,\s*\d+,\s*\d+,\s*\d+,\s*[\w\s]+)\]', response)# Convert each group into a list of integers and labels.parsed_boxes = []for box in bounding_boxes:parts = box.split(',')numbers = list(map(int, parts[:-1]))label = parts[-1].strip()parsed_boxes.append((numbers, label))# Return the list of bounding boxes with their labels.return parsed_boxesbounding_box = parse_bounding_box(result)
label_colors = {}def draw_bounding_boxes(image, bounding_boxes_with_labels):if image.mode != 'RGB':image = image.convert('RGB')image = np.array(image)for bounding_box, label in bounding_boxes_with_labels:# Normalize the bounding box coordinates.height = image.shape[1], image.shape[0]xmin, ymax, xmax = bounding_boxx1 = int(xmin / 1000 * width)y1 = int(ymin / 1000 * height)x2 = int(xmax / 1000 * width)y2 = int(ymax / 1000 * height)if label not in label_colors:color = np.random.randint(0, 256, (3,)).tolist()= colorelse:color = label_colors[label]font = cv2.FONT_HERSHEY_SIMPLEXfont_scale = 0.5font_thickness = 1box_thickness = 2text_size = cv2.getTextSize(label, font, font_scale, font_thickness)[0]text_bg_x1 = x1text_bg_y1 = y1 - text_size[1] - 5text_bg_x2 = x1 + text_size[0] + 8text_bg_y2 = y1(text_bg_x1, text_bg_y1), (text_bg_x2, text_bg_y2), color, -1)label, (x1 + 2, y1 - 5), font, font_scale, (255, 255, 255), font_thickness)(x1, y1), (x2, y2), color, box_thickness)image = Image.fromarray(image)return imageoutput = draw_bounding_boxes(img, bounding_box)
下载1：OpenCV-Contrib扩展模块中文版教程 在「小白学视觉」公众号后台回复：扩展模块中文教程，即可下载全网第一份OpenCV扩展模块教程中文版，涵盖扩展模块安装、SFM算法、立体视觉、目标跟踪、生物视觉、超分辨率处理等二十多章内容。 下载2：Python视觉实战项目52讲 在「小白学视觉」公众号后台回复：Python视觉实战项目，即可下载包括图像分割、口罩检测、车道线检测、车辆计数、添加眼线、车牌识别、字符识别、情绪检测、文本内容提取、面部识别等31个视觉实战项目，助力快速学校计算机视觉。 下载3：OpenCV实战项目20讲 在「小白学视觉」公众号后台回复：OpenCV实战项目20讲，即可下载含有20个基于OpenCV实现20个实战项目，实现OpenCV学习进阶。 交流群
欢迎加入公众号读者群一起和同行交流，目前有SLAM、三维视觉、传感器、自动驾驶、计算摄影、检测、分割、识别、医学影像、GAN、算法竞赛等微信群（以后会逐渐细分），请扫描下面微信号加群，备注：”昵称+学校/公司+研究方向“，例如：”张三 + 上海交大 + 视觉SLAM“。请按照格式备注，否则不予通过。添加成功后会根据研究方向邀请进入相关微信群。请勿在群内发送广告，否则会请出群，谢谢理解~
