使用零样本目标检测识别物体 | 附代码

# 导入必要的库from transformers import pipeline

# 从Hugging Face模型中心加载特定检查点checkpoint = “google/owlv2-base-patch16-ensemble”detector = pipeline(model=checkpoint, task=”zero-shot-object-detection”)

# 导入图像处理库import skimageimport numpy as npfrom PIL import Imageimport matplotlib.pyplot as plt

# 加载并显示图像image = Image.open(‘/content/image2.jpg’)plt.imshow(image)plt.axis(‘off’)plt.show()image = Image.fromarray(np.uint8(image)).convert(“RGB”)

# 定义候选标签并在图像上运行检测器predictions = detector(    image,    candidate_labels=[“fanta”, “cokacola”, “bottle”, “egg”, “bowl”, “donut”, “milk”, “jar”, “curd”, “pickle”, “refrigerator”, “fruits”, “vegetables”, “bread”,”yogurt”],)predictions

[{'score': 0.4910733997821808,  'label': 'bottle',  'box': {'xmin': 419, 'ymin': 1825, 'xmax': 574, 'ymax': 2116}}, {'score': 0.45601949095726013,  'label': 'bottle',  'box': {'xmin': 1502, 'ymin': 795, 'xmax': 1668, 'ymax': 1220}}, {'score': 0.4522128999233246,  'label': 'bottle',  'box': {'xmin': 294, 'ymin': 1714, 'xmax': 479, 'ymax': 1924}}, {'score': 0.4485340714454651,  'label': 'milk',  'box': {'xmin': 545, 'ymin': 811, 'xmax': 770, 'ymax': 1201}}, {'score': 0.44276902079582214,  'label': 'bottle',  'box': {'xmin': 1537, 'ymin': 958, 'xmax': 1681, 'ymax': 1219}}, {'score': 0.4287840723991394,  'label': 'bottle',  'box': {'xmin': 264, 'ymin': 1726, 'xmax': 459, 'ymax': 2104}}, {'score': 0.41883620619773865,  'label': 'bottle',  'box': {'xmin': 547, 'ymin': 632, 'xmax': 773, 'ymax': 1203}}, {'score': 0.15758953988552094,  'label': 'jar',  'box': {'xmin': 1141, 'ymin': 1628, 'xmax': 1259, 'ymax': 1883}}, {'score': 0.15696804225444794,  'label': 'egg',  'box': {'xmin': 296, 'ymin': 1034, 'xmax': 557, 'ymax': 1131}}, {'score': 0.15674084424972534,  'label': 'egg',  'box': {'xmin': 292, 'ymin': 1109, 'xmax': 552, 'ymax': 1212}}, {'score': 0.1565699428319931,  'label': 'coke',  'box': {'xmin': 294, 'ymin': 1714, 'xmax': 479, 'ymax': 1924}}, {'score': 0.15651869773864746,  'label': 'milk',  'box': {'xmin': 417, 'ymin': 1324, 'xmax': 635, 'ymax': 1450}}]

from PIL import ImageDrawdraw = ImageDraw.Draw(image)for prediction in predictions:    box = prediction[“box”]    label = prediction[“label”]    score = prediction[“score”]    xmin, ymin, xmax, ymax = box.values()    draw.rectangle((xmin, ymin, xmax, ymax), outline=”red”, width=1)    draw.text((xmin, ymin), f”{label}: {round(score,2)}”, fill=”white”)image

# 提取检测到的物体的函数def get_detected_objects(predictions):    detected_objects = [pred[“label”] for pred in predictions]    return detected_objects

# 打印检测到的物体列表detected_objects = get_detected_objects(predictions)print(“Detected Objects:”, detected_objects)

Detected Objects: [‘bottle’, ‘bottle’, ‘bottle’, ‘milk’, ‘bottle’, ‘bottle’, ‘bottle’, ‘coke’, ‘jar’, ‘milk’, ‘refrigerator’, ‘jar’, ‘jar’, ‘refrigerator’, ‘bottle’, ‘jar’, ‘yogurt’, ‘yogurt’, ‘refrigerator’, ‘bottle’, ‘jar’, ‘vegetables’, ‘bottle’, ‘jar’, ‘coke’, ‘jar’, ‘yogurt’, ‘coke’, ‘yogurt’, ‘milk’, ‘coke’, ‘egg’, ‘egg’, ‘bottle’, ‘vegetables’, ‘milk’, ‘coke’, ‘fruits’, ‘vegetables’, ‘milk’, ‘jar’, ‘jar’, ‘bottle’, ‘yogurt’, ‘refrigerator’, ‘milk’, ‘milk’, ‘coke’, ‘bottle’, ‘coke’, ‘egg’, ‘yogurt’, ‘bottle’, ‘milk’, ‘refrigerator’, ‘bottle’, ‘bottle’, ‘egg’, ‘bottle’, ‘milk’, ‘egg’, ‘bottle’, ‘milk’, ‘curd’, ‘coke’, ‘bowl’, ‘vegetables’, ‘milk’, ‘milk’, ‘coke’, ‘egg’, ‘bottle’, ‘curd’, ‘egg’, ‘egg’, ‘yogurt’, ‘egg’, ‘bottle’, ‘egg’, ‘jar’, ‘egg’, ‘egg’, ‘coke’, ‘milk’, ‘vegetables’, ‘curd’, ‘bottle’, ‘jar’, ‘egg’, ‘yogurt’, ‘milk’, ‘egg’, ‘fruits’, ‘yogurt’, ‘jar’, ‘milk’, ‘milk’, ‘curd’, ‘fruits’, ‘curd’, ‘yogurt’, ‘yogurt’, ‘yogurt’, ‘egg’, ‘coke’, ‘egg’, ‘refrigerator’, ‘cokacola’, ‘curd’, ‘jar’, ‘bottle’, ‘refrigerator’, ‘bottle’, ‘milk’, ‘milk’, ‘coke’, ‘curd’, ‘yogurt’, ‘fruits’, ‘yogurt’, ‘vegetables’, ‘yogurt’, ‘coke’, ‘cokacola’, ‘egg’, ‘milk’, ‘milk’, ‘egg’, ‘coke’, ‘coke’, ‘curd’, ‘cokacola’, ‘jar’, ‘jar’, ‘bottle’, ‘curd’, ‘coke’, ‘yogurt’, ‘curd’, ‘fruits’, ‘refrigerator’, ‘milk’, ‘fruits’, ‘cokacola’, ‘milk’, ‘cokacola’, ‘egg’, ‘yogurt’, ‘pickle’, ‘fruits’, ‘coke’, ‘pickle’, ‘egg’, ‘fruits’, ‘refrigerator’, ‘refrigerator’, ‘bottle’, ‘curd’, ‘egg’, ‘egg’, ‘bottle’, ‘refrigerator’, ‘egg’, ‘jar’, ‘jar’, ‘bottle’, ‘pickle’, ‘egg’, ‘jar’, ‘cokacola’, ‘yogurt’, ‘milk’, ‘curd’, ‘bottle’, ‘milk’, ‘milk’, ‘cokacola’, ‘bottle’]

# 使用额外的标签再次运行检测器predictions = detector(    image,    candidate_labels=[“fanta”, “cokacola”, “pepsi”, “mountain dew”, “sprite”, “pepper”, “sangria”, “vitamin water”, “beer”],)

from PIL import ImageDrawdraw = ImageDraw.Draw(image)for prediction in predictions:    box = prediction[“box”]    label = prediction[“label”]    score = prediction[“score”]    xmin, ymin, xmax, ymax = box.values()    draw.rectangle((xmin, ymin, xmax, ymax), outline=”red”, width=1)    draw.text((xmin, ymin), f”{label}: {round(score,2)}”, fill=”white”)image