代码回滚：增加未知类别负样本之后，模型不收敛，训练效果特别差，现在进行回滚。回滚之后效果非常不错。

classifier/embedding_food_classifier_app.py

@@ -65,12 +65,14 @@ class EmbeddingFoodClassifierApp:
             BASE_DIR = os.path.dirname(os.path.abspath(__file__))
             # model_path = "../model/embedding_20251011_133653/best_embedding_model.pth"
             # model_path = os.path.join(BASE_DIR, "../model/embedding_20251011_133653/best_embedding_model.pth")
-            model_path = os.path.join(BASE_DIR, "../model/WholeIngredientRecognition/embedding_20251021_085915/best_embedding_model.pth")
+            model_path = os.path.join(BASE_DIR, "../model/ProcessedIngredientRecognition/embedding_20251029_100204/best_embedding_model.pth")
+            # model_path = os.path.join(BASE_DIR, "../model/WholeIngredientRecognition/embedding_20251024_091151/best_embedding_model.pth")
             # model_path = os.path.join(BASE_DIR, "../model/DishClassification/embedding_20251022_093635/best_embedding_model.pth")
 
             # FAISS索引目录
             # index_dir = "../faiss_vector_db/faiss_index"
             # index_dir = os.path.join(BASE_DIR, "../faiss_vector_db/faiss_index")
+            index_dir = os.path.join(BASE_DIR, "../faiss_vector_db/ProcessedIngredientRecognition/faiss_index")
             index_dir = os.path.join(BASE_DIR, "../faiss_vector_db/WholeIngredientRecognition/faiss_index")
             # index_dir = os.path.join(BASE_DIR, "../faiss_vector_db/DishClassification/faiss_index")
 
@@ -1087,12 +1089,13 @@ class EmbeddingFoodClassifierApp:
         """识别所有图片"""
         try:
             self.current_results.clear()
-            
+            score_list = []
             for i, img_info in enumerate(self.uploaded_images):
                 # 使用embedding相似度识别
                 if self.model is not None and self.faiss_index is not None:
                     # 使用真实的embedding模型和FAISS索引
-                    predicted_class, confidence, similar_images = self.predict_with_embedding(img_info['image'])
+                    predicted_class, confidence, similar_images,score = self.predict_with_embedding(img_info['image'])
+                    score_list.append(score)
                 else:
                     # 模拟预测结果
                     predicted_class = np.random.choice(self.class_names)
@@ -1122,7 +1125,7 @@ class EmbeddingFoodClassifierApp:
                 
                 # 更新UI（在主线程中）
                 self.root.after(0, self.update_progress, i + 1, len(self.uploaded_images))
-            
+            print('socre_list',score_list)
             # 识别完成，更新UI
             self.root.after(0, self.recognition_completed)
             
@@ -1144,8 +1147,10 @@ class EmbeddingFoodClassifierApp:
             
             # 在FAISS索引中搜索最相似的k张图片
             scores, indices = self.faiss_index.search(query_embedding, k)
-            print("最相似的图片索引:", indices)
+            # print("最相似的图片索引:", indices)
-            print("最相似的图片分数:", scores)
+            # print("最相似的图片分数:", type(scores[0]))
+            # print("最相似的图片分数:", scores[0,0])
+            # print("最相似的图片分数:", type(scores[0,0]))
 
             # 收集相似图片的类别
             similar_classes = []
@@ -1179,12 +1184,12 @@ class EmbeddingFoodClassifierApp:
                 vote_ratio = class_counts[predicted_class] / len(similar_classes)
                 confidence = max_score * vote_ratio
                 
-                return predicted_class, confidence, similar_images
+                return predicted_class, confidence, similar_images,round(scores[0,0],3)
             else:
                 # 如果没有找到相似图片，随机选择一个类别
                 predicted_class = np.random.choice(self.class_names)
                 confidence = 0.1
-                return predicted_class, confidence, []
+                return predicted_class, confidence, [],scores[0,0]
                 
         except Exception as e:
             print(f"Embedding预测出错: {e}")

faiss_vector_db/build_faiss_index.py

@@ -480,12 +480,15 @@ def main():
     """主函数"""
     # 配置参数
     # MODEL_PATH = "../model/embedding_20251011_133653/best_embedding_model.pth"
-    # MODEL_PATH = "../model/WholeIngredientRecognition/embedding_20251021_085915/best_embedding_model.pth"
+    MODEL_PATH = "../model/ProcessedIngredientRecognition/embedding_20251029_100204/best_embedding_model.pth"
-    MODEL_PATH = "../model/DishClassification/embedding_20251022_093635/best_embedding_model.pth"
+    # MODEL_PATH = "../model/WholeIngredientRecognition/embedding_20251024_091151/best_embedding_model.pth"
+    # MODEL_PATH = "../model/DishClassification/embedding_20251022_093635/best_embedding_model.pth"
+    TRAIN_DIR = "../dataset/ProcessedIngredientRecognition/train"
     # TRAIN_DIR = "../dataset/WholeIngredientRecognition/train"
-    TRAIN_DIR = "../dataset/DishClassification/train"
+    # TRAIN_DIR = "../dataset/DishClassification/train"
+    OUTPUT_DIR = "ProcessedIngredientRecognition/faiss_index"
     # OUTPUT_DIR = "WholeIngredientRecognition/faiss_index"
-    OUTPUT_DIR = "DishClassification/faiss_index"
+    # OUTPUT_DIR = "DishClassification/faiss_index"
     BATCH_SIZE = 16
     INDEX_TYPE = 'flat'  # 'flat', 'ivf', 'hnsw'
     EMBEDDING_DIM = 512

faiss_vector_db/visualize_embeddings.py

@@ -162,10 +162,12 @@ def plot_2d(Z: np.ndarray, y: np.ndarray, title: str, out_path: Optional[str] =
 
 def main():
     parser = argparse.ArgumentParser(description="可视化高维 embedding 并进行坍塌诊断")
-    parser.add_argument("--embeddings", type=str, default=os.path.join("DishClassification/faiss_index", "embeddings.json"), help="embeddings.json 路径")
+    # parser.add_argument("--embeddings", type=str, default=os.path.join("DishClassification/faiss_index", "embeddings.json"), help="embeddings.json 路径")
     # parser.add_argument("--embeddings", type=str, default=os.path.join("WholeIngredientRecognition/faiss_index", "embeddings.json"), help="embeddings.json 路径")
-    parser.add_argument("--labels", type=str, default=os.path.join("DishClassification/faiss_index", "labels.json"), help="labels.json 路径")
+    parser.add_argument("--embeddings", type=str, default=os.path.join("ProcessedIngredientRecognition/faiss_index", "embeddings.json"), help="embeddings.json 路径")
+    # parser.add_argument("--labels", type=str, default=os.path.join("DishClassification/faiss_index", "labels.json"), help="labels.json 路径")
     # parser.add_argument("--labels", type=str, default=os.path.join("WholeIngredientRecognition/faiss_index", "labels.json"), help="labels.json 路径")
+    parser.add_argument("--labels", type=str, default=os.path.join("ProcessedIngredientRecognition/faiss_index", "labels.json"), help="labels.json 路径")
     parser.add_argument("--method", type=str, default="pca", choices=["pca", "tsne", "umap"], help="降维方法")
     parser.add_argument("--seed", type=int, default=42)
     parser.add_argument("--max_points", type=int, default=None, help="抽样上限，避免t-SNE/UMAP过慢；None为全量")

train/train_embedding.py

@@ -73,9 +73,11 @@ TASKS = {
         embedding_dim=512,
         batch_size=16,
         lr=1e-3,
-        triplet_margin=0.25,
+        # triplet_margin=0.25,
-        center_loss_weight=0.1,
+        triplet_margin=0.5,
-        aug_strength="shape",
+        # center_loss_weight=0.5,
+        center_loss_weight=20,
+        aug_strength="medium",
     ),
 }
 
@@ -818,5 +820,6 @@ if __name__ == "__main__":
     parser = argparse.ArgumentParser()
     parser.add_argument("task", choices=list(TASKS.keys()), nargs="?", default="dish")
     args = parser.parse_args()
+    main("processed_ingredient")
     # main("whole_ingredient")
-    main("dish")
+    # main("dish")