Create utils.py

utils/utils.py

@@ -0,0 +1,43 @@
+# utils.py
+import torch
+import supervision as sv
+from PIL import Image
+
+def detect_objects_in_image(image_input_path, texts, device):
+    # 加载图像
+    image_input = Image.open(image_input_path)
+
+    # 初始化检测列表
+    detections_list = []
+
+    # 对每个文本进行检测
+    for text in texts:
+        _, result = run_florence_inference(
+            model=FLORENCE_MODEL.to(device),
+            processor=FLORENCE_PROCESSOR,
+            device=device,
+            image=image_input,
+            task=FLORENCE_OPEN_VOCABULARY_DETECTION_TASK,
+            text=text
+        )
+
+        # 从结果中构建监督检测对象
+        detections = sv.Detections.from_lmm(
+            lmm=sv.LMM.FLORENCE_2,
+            result=result,
+            resolution_wh=image_input.size
+        )
+
+        # 运行 SAM 推理
+        detections = run_sam_inference(SAM_IMAGE_MODEL.to(device), image_input, detections)
+
+        # 将检测结果添加到列表中
+        detections_list.append(detections)
+
+    # 合并所有检测结果
+    detections = sv.Detections.merge(detections_list)
+
+    # 再次运行 SAM 推理
+    detections = run_sam_inference(SAM_IMAGE_MODEL.to(device), image_input, detections)
+
+    return detections