yixiong/FoodClassifier
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

修改build_faiss_index.py,增加cosFace训练脚本。增加加载cosFace模型的逻辑。

Browse Source
This commit is contained in:
zhangpu
2025-11-06 10:45:09 +08:00
parent a81de1f4ce
commit 2c74c81918
3 changed files with 35 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
classifier/embedding_food_classifier_app.py
+8 -4
View File
@@ -65,16 +65,16 @@ class EmbeddingFoodClassifierApp:
BASE_DIR = os.path.dirname(os.path.abspath(__file__)) BASE_DIR = os.path.dirname(os.path.abspath(__file__))
# model_path = "../model/embedding_20251011_133653/best_embedding_model.pth" # 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/embedding_20251011_133653/best_embedding_model.pth")
model_path = os.path.join(BASE_DIR, "../model/ProcessedIngredientRecognition/embedding_20251029_170904/best_embedding_model.pth") # model_path = os.path.join(BASE_DIR, "../model/ProcessedIngredientRecognition/embedding_20251029_170904/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/WholeIngredientRecognition/embedding_20251024_091151/best_embedding_model.pth")
# model_path = os.path.join(BASE_DIR, "../model/DishClassification/embedding_20251022_093635/best_embedding_model.pth") model_path = os.path.join(BASE_DIR, "../model/DishClassification/cosface_20251105_200551/best_cosface_model.pth")
# FAISS索引目录 # FAISS索引目录
# index_dir = "../faiss_vector_db/faiss_index" # 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/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/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/WholeIngredientRecognition/faiss_index")
# index_dir = os.path.join(BASE_DIR, "../faiss_vector_db/DishClassification/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): if os.path.exists(model_path) and os.path.exists(index_dir):
# 1. 加载embedding模型 # 1. 加载embedding模型
@@ -91,6 +91,10 @@ class EmbeddingFoodClassifierApp:
if isinstance(checkpoint, dict): if isinstance(checkpoint, dict):
if 'model_state_dict' in checkpoint: if 'model_state_dict' in checkpoint:
self.model.load_state_dict(checkpoint['model_state_dict']) self.model.load_state_dict(checkpoint['model_state_dict'])
elif 'backbone_state_dict' in checkpoint:
# CosFace格式：使用backbone_state_dict（只加载backbone部分）
self.model.load_state_dict(checkpoint['backbone_state_dict'])
print("检测到CosFace模型格式，使用'backbone_state_dict'加载")
elif 'state_dict' in checkpoint: elif 'state_dict' in checkpoint:
self.model.load_state_dict(checkpoint['state_dict']) self.model.load_state_dict(checkpoint['state_dict'])
else: else:
faiss_vector_db/build_faiss_index.py
+23 -6
View File
@@ -75,13 +75,25 @@ class FAISSIndexBuilder:
# 处理不同的保存格式 # 处理不同的保存格式
if isinstance(checkpoint, dict): if isinstance(checkpoint, dict):
if 'model_state_dict' in checkpoint: if 'model_state_dict' in checkpoint:
# Triplet格式：使用model_state_dict
self.model.load_state_dict(checkpoint['model_state_dict']) self.model.load_state_dict(checkpoint['model_state_dict'])
print("检测到Triplet模型格式，使用'model_state_dict'加载")
elif 'backbone_state_dict' in checkpoint:
# CosFace格式：使用backbone_state_dict（只加载backbone部分）
self.model.load_state_dict(checkpoint['backbone_state_dict'])
print("检测到CosFace模型格式，使用'backbone_state_dict'加载")
elif 'state_dict' in checkpoint: elif 'state_dict' in checkpoint:
# 通用格式：使用state_dict
self.model.load_state_dict(checkpoint['state_dict']) self.model.load_state_dict(checkpoint['state_dict'])
print("检测到通用模型格式，使用'state_dict'加载")
else: else:
# 直接加载整个checkpoint作为state_dict
self.model.load_state_dict(checkpoint) self.model.load_state_dict(checkpoint)
print("使用checkpoint直接加载")
else: else:
# checkpoint本身就是state_dict
self.model.load_state_dict(checkpoint) self.model.load_state_dict(checkpoint)
print("checkpoint为state_dict格式，直接加载")
# 移动到设备并设置为评估模式 # 移动到设备并设置为评估模式
self.model.to(self.device) self.model.to(self.device)
@@ -408,6 +420,10 @@ class FAISSSearcher:
if isinstance(checkpoint, dict): if isinstance(checkpoint, dict):
if 'model_state_dict' in checkpoint: if 'model_state_dict' in checkpoint:
self.model.load_state_dict(checkpoint['model_state_dict']) self.model.load_state_dict(checkpoint['model_state_dict'])
elif 'backbone_state_dict' in checkpoint:
# CosFace格式：使用backbone_state_dict（只加载backbone部分）
self.model.load_state_dict(checkpoint['backbone_state_dict'])
print("检测到CosFace模型格式，使用'backbone_state_dict'加载")
elif 'state_dict' in checkpoint: elif 'state_dict' in checkpoint:
self.model.load_state_dict(checkpoint['state_dict']) self.model.load_state_dict(checkpoint['state_dict'])
else: else:
@@ -480,16 +496,17 @@ def main():
"""主函数""" """主函数"""
# 配置参数 # 配置参数
# MODEL_PATH = "../model/embedding_20251011_133653/best_embedding_model.pth" # MODEL_PATH = "../model/embedding_20251011_133653/best_embedding_model.pth"
MODEL_PATH = "../model/ProcessedIngredientRecognition/embedding_20251103_172012/best_embedding_model.pth" # MODEL_PATH = "../model/ProcessedIngredientRecognition/embedding_20251103_172012/best_embedding_model.pth"
# MODEL_PATH = "../model/WholeIngredientRecognition/embedding_20251030_135024/best_embedding_model.pth" # MODEL_PATH = "../model/WholeIngredientRecognition/embedding_20251030_135024/best_embedding_model.pth"
# MODEL_PATH = "../model/DishClassification/embedding_20251022_093635/best_embedding_model.pth" # MODEL_PATH = "../model/DishClassification/cosface_20251105_200551/best_embedding_model.pth"
TRAIN_DIR = "../dataset/ProcessedIngredientRecognition/train" MODEL_PATH = "../model/DishClassification/cosface_20251105_200551/best_cosface_model.pth"
# TRAIN_DIR = "../dataset/ProcessedIngredientRecognition/train"
# TRAIN_DIR = "../dataset/WholeIngredientRecognition/train" # TRAIN_DIR = "../dataset/WholeIngredientRecognition/train"
# TRAIN_DIR = "../dataset/DishClassification/train" TRAIN_DIR = "../dataset/DishClassification/train"
OUTPUT_DIR = "ProcessedIngredientRecognition/faiss_index" # OUTPUT_DIR = "ProcessedIngredientRecognition/faiss_index"
# OUTPUT_DIR = "WholeIngredientRecognition/faiss_index" # OUTPUT_DIR = "WholeIngredientRecognition/faiss_index"
# OUTPUT_DIR = "DishClassification/faiss_index" OUTPUT_DIR = "DishClassification/faiss_index"
BATCH_SIZE = 16 BATCH_SIZE = 16
INDEX_TYPE = 'flat' # 'flat', 'ivf', 'hnsw' INDEX_TYPE = 'flat' # 'flat', 'ivf', 'hnsw'
EMBEDDING_DIM = 512 EMBEDDING_DIM = 512
faiss_vector_db/visualize_embeddings.py
+4 -4
View File
@@ -162,12 +162,12 @@ def plot_2d(Z: np.ndarray, y: np.ndarray, title: str, out_path: Optional[str] =
def main(): def main():
parser = argparse.ArgumentParser(description="可视化高维 embedding 并进行坍塌诊断") 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("--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("--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("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("--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("--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("--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") 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")