diff --git a/classifier/embedding_food_classifier_app.py b/classifier/embedding_food_classifier_app.py index b20ea27..956fad7 100644 --- a/classifier/embedding_food_classifier_app.py +++ b/classifier/embedding_food_classifier_app.py @@ -65,13 +65,15 @@ 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_20251023_120531/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/WholeIngredientRecognition/faiss_index102402") + 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") if os.path.exists(model_path) and os.path.exists(index_dir): diff --git a/faiss_vector_db/build_faiss_index.py b/faiss_vector_db/build_faiss_index.py index 0ad608f..d9dace3 100644 --- a/faiss_vector_db/build_faiss_index.py +++ b/faiss_vector_db/build_faiss_index.py @@ -480,11 +480,14 @@ 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/WholeIngredientRecognition/embedding_20251024_091151/best_embedding_model.pth" # MODEL_PATH = "../model/DishClassification/embedding_20251022_093635/best_embedding_model.pth" - TRAIN_DIR = "../dataset/WholeIngredientRecognition/train" + TRAIN_DIR = "../dataset/ProcessedIngredientRecognition/train" + # TRAIN_DIR = "../dataset/WholeIngredientRecognition/train" # TRAIN_DIR = "../dataset/DishClassification/train" - OUTPUT_DIR = "WholeIngredientRecognition/faiss_index" + OUTPUT_DIR = "ProcessedIngredientRecognition/faiss_index" + # OUTPUT_DIR = "WholeIngredientRecognition/faiss_index" # OUTPUT_DIR = "DishClassification/faiss_index" BATCH_SIZE = 16 INDEX_TYPE = 'flat' # 'flat', 'ivf', 'hnsw' diff --git a/faiss_vector_db/visualize_embeddings.py b/faiss_vector_db/visualize_embeddings.py index 1e67dc3..cab4355 100644 --- a/faiss_vector_db/visualize_embeddings.py +++ b/faiss_vector_db/visualize_embeddings.py @@ -163,9 +163,11 @@ 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("WholeIngredientRecognition/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("--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("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") diff --git a/train/train_embedding.py b/train/train_embedding.py index e77d97a..6f70fe6 100644 --- a/train/train_embedding.py +++ b/train/train_embedding.py @@ -32,7 +32,6 @@ class TaskConfig: name: str train_dir: str val_dir: str - unknown_dir: str # 未知类别数据目录 embedding_dim: int batch_size: int lr: float @@ -46,7 +45,6 @@ TASKS = { name="DishClassification", train_dir=os.path.join(settings.BASE_DIR, "dataset", "DishClassification", "train"), val_dir=os.path.join(settings.BASE_DIR, "dataset", "DishClassification", "val"), - unknown_dir=os.path.join(settings.BASE_DIR, "dataset", "Unknown", "DishClassification","train"), # 未知类别食物目录 embedding_dim=512, batch_size=16, lr=1e-3, @@ -60,7 +58,6 @@ TASKS = { name="WholeIngredientRecognition", train_dir=os.path.join(settings.BASE_DIR, "dataset", "WholeIngredientRecognition", "train"), val_dir=os.path.join(settings.BASE_DIR, "dataset", "WholeIngredientRecognition", "val"), - unknown_dir=os.path.join(settings.BASE_DIR, "dataset", "Unknown","WholeIngredientRecognition", "train"), # 未知类别食物目录 embedding_dim=512, batch_size=32, lr=8e-4, @@ -73,13 +70,14 @@ TASKS = { name="ProcessedIngredientRecognition", train_dir=os.path.join(settings.BASE_DIR, "dataset", "ProcessedIngredientRecognition", "train"), val_dir=os.path.join(settings.BASE_DIR, "dataset", "ProcessedIngredientRecognition", "val"), - unknown_dir=os.path.join(settings.BASE_DIR, "dataset", "Unknown", "ProcessedIngredientRecognition","train"), # 未知类别食物目录 embedding_dim=512, batch_size=16, lr=1e-3, - triplet_margin=0.25, - center_loss_weight=0.1, - aug_strength="shape", + # triplet_margin=0.25, + triplet_margin=0.5, + # center_loss_weight=0.5, + center_loss_weight=20, + aug_strength="medium", ), } @@ -147,7 +145,7 @@ class TripletDataset(Dataset): 每个样本包含：锚点(anchor)、正样本(positive)、负样本(negative) """ - def __init__(self, dataset_path: str, transform=None, samples_per_class: int = 100, unknown_dir: str = None, unknown_prob: float = 0.7): + def __init__(self, dataset_path: str, transform=None, samples_per_class: int = 100): """ 初始化三元组数据集 @@ -155,24 +153,18 @@ class TripletDataset(Dataset): dataset_path: 数据集路径 transform: 数据变换 samples_per_class: 每个类别最多使用的样本数 - unknown_dir: 未知类别数据目录 - unknown_prob: 使用未知类别作为负样本的概率 """ self.dataset_path = dataset_path self.transform = transform self.samples_per_class = samples_per_class - self.unknown_dir = unknown_dir - self.unknown_prob = unknown_prob # 加载数据集 self.class_to_idx = {} self.idx_to_class = {} self.samples_by_class = defaultdict(list) self.all_samples = [] - self.unknown_samples = [] # 未知类别样本列表 self._load_dataset() - self._load_unknown_samples() def _load_dataset(self): """加载数据集并按类别组织""" @@ -202,21 +194,6 @@ class TripletDataset(Dataset): for class_name, class_idx in self.class_to_idx.items(): logger.info(f" {class_name}: {len(self.samples_by_class[class_idx])} 张图片") - def _load_unknown_samples(self): - """加载未知类别样本""" - if not self.unknown_dir or not os.path.exists(self.unknown_dir): - logger.info("未指定未知类别目录或目录不存在，跳过未知样本加载") - return - - # 遍历未知类别目录下的所有图片 - for root, dirs, files in os.walk(self.unknown_dir): - for file in files: - if file.lower().endswith(('.png', '.jpg', '.jpeg')): - img_path = os.path.join(root, file) - self.unknown_samples.append(img_path) - - logger.info(f"加载未知类别样本完成: {len(self.unknown_samples)} 张图片") - def __len__(self): return len(self.all_samples) @@ -242,41 +219,16 @@ class TripletDataset(Dataset): positive_path = anchor_path # 如果只有一张图片，使用自己作为正样本 positive_img = self._load_image(positive_path) - # 获取负样本（使用策略选择未知类别或已知类别） - negative_img = self._get_negative_sample() - - return anchor_img, positive_img, negative_img, anchor_label - - def _get_negative_sample(self): - """ - 获取负样本，支持未知类别和已知类别的混合策略 - - Returns: - torch.Tensor: 负样本图片 - """ - # 如果有未知类别样本且概率满足条件，优先选择未知类别 - if self.unknown_samples and random.random() < self.unknown_prob: - # 选择未知类别作为负样本 - negative_path = random.choice(self.unknown_samples) - return self._load_image(negative_path) - - # 否则选择已知类别作为负样本（原来的逻辑） - # 为了安全起见，选择一个随机锚点 - anchor_idx = random.randint(0, len(self.all_samples) - 1) - anchor_path, anchor_label = self.all_samples[anchor_idx] - + # 获取负样本（不同类别的图片） # 获得其它类别 negative_classes = [cls for cls in self.samples_by_class.keys() if cls != anchor_label] - if negative_classes: - # 随便选一个类别 - negative_class = random.choice(negative_classes) - # 随便选一个路径 - negative_path = random.choice(self.samples_by_class[negative_class]) - else: - # 如果没有其他类别，使用自己作为负样本（这种情况应该很少见） - negative_path = anchor_path + # 随便选一个类别 + negative_class = random.choice(negative_classes) + # 随便选一个路径 + negative_path = random.choice(self.samples_by_class[negative_class]) + negative_img = self._load_image(negative_path) - return self._load_image(negative_path) + return anchor_img, positive_img, negative_img, anchor_label def _load_image(self, image_path: str): """加载并预处理图片""" @@ -694,17 +646,13 @@ def main(task_key: str = "dish"): train_dataset = TripletDataset( dataset_path=cfg.train_dir, transform=transform_train, - samples_per_class=550, - unknown_dir=cfg.unknown_dir, - unknown_prob=0.7 # 70%概率使用未知类别作为负样本 + samples_per_class=550 ) - + val_dataset = TripletDataset( dataset_path=cfg.val_dir, transform=transform_val, - samples_per_class=50, - unknown_dir=cfg.unknown_dir, - unknown_prob=0.7 # 70%概率使用未知类别作为负样本 + samples_per_class=50 ) # 创建数据加载器 @@ -872,5 +820,6 @@ if __name__ == "__main__": parser = argparse.ArgumentParser() parser.add_argument("task", choices=list(TASKS.keys()), nargs="?", default="dish") args = parser.parse_args() - main("whole_ingredient") + main("processed_ingredient") + # main("whole_ingredient") # main("dish") \ No newline at end of file