From 909018b3ec0bf66620cb1adbbf3759ab678d6ab0 Mon Sep 17 00:00:00 2001 From: liuwei Date: Mon, 14 Apr 2025 12:09:10 +0800 Subject: [PATCH] =?UTF-8?q?feature=EF=BC=9A=E5=8A=A0=E5=85=A5=E5=8A=9F?= =?UTF-8?q?=E8=83=BD=EF=BC=8C=E5=B0=8F=E6=9C=8B=E5=8F=8B=E4=BA=BA=E8=84=B8?= =?UTF-8?q?=E8=AF=86=E5=88=AB=E4=B8=8E=E5=88=86=E7=B1=BB=E3=80=82?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- plugins/kid_photo_extractor/main.py | 74 +++++++++++++++++++++++++---- 1 file changed, 64 insertions(+), 10 deletions(-) diff --git a/plugins/kid_photo_extractor/main.py b/plugins/kid_photo_extractor/main.py index bbfc1e0..7f6805d 100644 --- a/plugins/kid_photo_extractor/main.py +++ b/plugins/kid_photo_extractor/main.py @@ -101,13 +101,34 @@ class FaceAnalyzer: return None # 提取人脸特征向量用于后续比对 - embedding = DeepFace.represent( + embedding_result = DeepFace.represent( img_path=image_path, model_name='Facenet', enforce_detection=False, detector_backend='opencv' # 使用更快的opencv检测器 ) + # 处理embedding结果，确保它是一个数值数组 + embedding = None + if isinstance(embedding_result, list) and len(embedding_result) > 0: + if isinstance(embedding_result[0], dict) and 'embedding' in embedding_result[0]: + embedding = embedding_result[0]['embedding'] + else: + embedding = embedding_result[0] + elif isinstance(embedding_result, dict) and 'embedding' in embedding_result: + embedding = embedding_result['embedding'] + else: + embedding = embedding_result + + # 确保embedding是数值列表 + if embedding is not None: + try: + # 尝试转换为浮点数列表 + embedding = [float(x) for x in embedding] + except (TypeError, ValueError): + self.logger.error(f"无法将嵌入向量转换为浮点数列表: {image_path}") + return None + self.logger.info(f"成功提取人脸特征向量: {image_path}") # 如果使用了临时文件，删除它 @@ -142,7 +163,6 @@ class FaceGrouper: self.min_samples = min_samples # 形成核心点所需的最小样本数 self.logger = logging.getLogger("Plugin.KidPhotoExtractor.FaceGrouper") - # 在 FaceGrouper 类的 cluster_faces 方法中，优化性能和错误处理 def cluster_faces(self, face_embeddings): """对人脸特征向量进行聚类""" if not face_embeddings: @@ -153,14 +173,36 @@ class FaceGrouper: return [0] * len(face_embeddings) try: - # 将特征向量转换为numpy数组 - embeddings_array = np.array(face_embeddings) + # 将特征向量转换为numpy数组，确保是浮点数类型 + # 首先提取实际的嵌入向量数据 + processed_embeddings = [] + for emb in face_embeddings: + # DeepFace.represent() 可能返回字典或列表，需要提取实际的向量 + if isinstance(emb, dict) and 'embedding' in emb: + processed_embeddings.append(emb['embedding']) + elif isinstance(emb, list) and len(emb) > 0: + # 如果是列表，取第一个元素 + if isinstance(emb[0], dict) and 'embedding' in emb[0]: + processed_embeddings.append(emb[0]['embedding']) + else: + processed_embeddings.append(emb) + else: + processed_embeddings.append(emb) - # 检查数据有效性 - if np.isnan(embeddings_array).any() or np.isinf(embeddings_array).any(): - self.logger.error("特征向量包含无效值(NaN或Inf)") - # 清理无效值 - embeddings_array = np.nan_to_num(embeddings_array) + # 转换为numpy数组并确保是浮点数类型 + embeddings_array = np.array(processed_embeddings, dtype=np.float64) + + # 安全地检查无效值 + try: + has_nan = np.isnan(embeddings_array).any() + has_inf = np.isinf(embeddings_array).any() + if has_nan or has_inf: + self.logger.error("特征向量包含无效值(NaN或Inf)") + # 清理无效值 + embeddings_array = np.nan_to_num(embeddings_array) + except TypeError: + # 如果仍然无法检查NaN/Inf，记录警告并继续 + self.logger.warning("无法检查特征向量中的无效值，将直接进行聚类") # 使用DBSCAN进行聚类 clustering = DBSCAN(eps=self.eps, min_samples=self.min_samples, metric='euclidean').fit(embeddings_array) @@ -654,9 +696,21 @@ class KidPhotoExtractorPlugin(MessagePluginInterface): person_folder = os.path.join(output_dir, f"person_{person_id}") os.makedirs(person_folder, exist_ok=True) - # 复制照片 + # 复制照片 - 修改为只复制原始照片，不复制人脸区域 copied_photos = [] + processed_paths = set() # 用于跟踪已处理的照片路径，避免重复复制 + for image_path, _ in faces: + # 跳过临时文件 + if ".temp." in image_path: + continue + + # 避免重复复制同一张照片 + if image_path in processed_paths: + continue + + processed_paths.add(image_path) + if self.photo_classifier.copy_photo(image_path, person_folder): copied_photos.append(os.path.basename(image_path)) # 保存照片映射关系