hjxdl 0.1.64__py3-none-any.whl → 0.1.66__py3-none-any.whl

hdl/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.64'
-__version_tuple__ = version_tuple = (0, 1, 64)
+__version__ = version = '0.1.66'
+__version_tuple__ = version_tuple = (0, 1, 66)

hdl/utils/llm/vis.py

@@ -6,6 +6,7 @@ import numpy as np
 from PIL import Image
 # from transformers import ChineseCLIPProcessor, ChineseCLIPModel
 import open_clip
+import natsort
 
 from ..database_tools.connect import conn_redis
 
@@ -20,27 +21,43 @@ class ImgHandler:
     def __init__(
         self,
         model_path,
-        redis_host,
-        redis_port,
+        db_host,
+        db_port,
         model_name: str = None,
-        device: str = None
+        device: str = "cpu",
+        num_vec_dim: int = None,
+        load_model: bool = True,
     ) -> None:
-        if device is None:
-            self.device = torch.device("cuda") \
-                if torch.cuda.is_available() \
-                else torch.device("cpu")
-        else:
-            self.device = device
+
+        self.device = torch.device(device)
+        self.model_path = model_path
+        self.model_name = model_name
+
+        self.db_host = db_host
+        self.db_port = db_port
+        self._db_conn = None
+        self.num_vec_dim = num_vec_dim
+        if load_model:
+            self.load_model()
+
+    def load_model(self):
+        """Load the OpenCLIP model and related configurations.
+
+        This function loads the OpenCLIP model from the specified model path
+        and initializes the necessary components such as the model,
+        preprocessors for training and validation data, tokenizer, etc.
+
+        Returns:
+            None
+        """
         ckpt_file = (
-            Path(model_path) / Path("open_clip_pytorch_model.bin")
+            Path(self.model_path) / Path("open_clip_pytorch_model.bin")
         ).as_posix()
-
         self.open_clip_cfg = json.load(
-            open(Path(model_path) / Path("open_clip_config.json"))
+            open(Path(self.model_path) / Path("open_clip_config.json"))
         )
-        if model_name is not None:
-            self.model_name = model_name
-        else:
+
+        if self.model_name is None:
             self.model_name = (
                 self.open_clip_cfg['model_cfg']['text_cfg']['hf_tokenizer_name']
                 .split('/')[-1]
@@ -54,27 +71,22 @@ class ImgHandler:
                 # precision=precision
             )
         )
-        self.vector_dimension = self.open_clip_cfg["model_cfg"]["embed_dim"]
+        if self.num_vec_dim is None:
+            self.num_vec_dim = self.open_clip_cfg["model_cfg"]["embed_dim"]
         self.tokenizer = open_clip.get_tokenizer(
-            HF_HUB_PREFIX + model_path
+            HF_HUB_PREFIX + self.model_path
         )
-        # self.model = ChineseCLIPModel.from_pretrained(model_path).to(self.device)
-        # self.processor = ChineseCLIPProcessor.from_pretrained(model_path)
-        self.redis_host = redis_host
-        self.redis_port = redis_port
-        self._redis_conn = None
-
 
     @property
-    def redis_conn(self):
+    def db_conn(self):
         """Establishes a connection to Redis server if not already connected.
 
             Returns:
                 Redis connection object: A connection to the Redis server.
         """
-        if self._redis_conn is None:
-            self._redis_conn = conn_redis(self.redis_host, self.redis_port)
-        return self._redis_conn
+        if self._db_conn is None:
+            self._db_conn = conn_redis(self.db_host, self.db_port)
+        return self._db_conn
 
     def get_img_features(
         self,
@@ -192,4 +204,27 @@ class ImgHandler:
             # > 0.9 很相似
             return sims
 
+    def vec_pics_todb(self, images):
+        """Save image features to a Redis database.
+
+        Args:
+            images (list): A list of image file paths.
+
+        Returns:
+            None
+
+        Example:
+            vec_pics_todb(images=['image1.jpg', 'image2.jpg'])
+        """
+        sorted_imgs = natsort.natsorted(images)
+        img_feats = self.get_img_features(sorted_imgs, to_numpy=True)
+        pipeline = self.ih.db_conn.pipeline()
+        for img_file, emb in zip(sorted_imgs, img_feats):
+            # 初始化 Redis，先使用 img 文件名作为 Key 和 Value，后续再更新为图片特征向量
+            pipeline.json().set(img_file, "$", img_file)
+            emb = emb.astype(np.float32).tolist()
+            pipeline.json().set(img_file, "$", emb)
+            res = pipeline.execute()
+            print('redis set:', res)
+
 

{hjxdl-0.1.64.dist-info → hjxdl-0.1.66.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hjxdl
-Version: 0.1.64
+Version: 0.1.66
 Summary: A collection of functions for Jupyter notebooks
 Home-page: https://github.com/huluxiaohuowa/hdl
 Author: Jianxing Hu
@@ -23,6 +23,7 @@ Requires-Dist: redis[hiredis]
 Requires-Dist: psycopg[binary]
 Requires-Dist: Pillow
 Requires-Dist: open-clip-torch
+Requires-Dist: natsort
 
 # DL framework by Jianxing
 

{hjxdl-0.1.64.dist-info → hjxdl-0.1.66.dist-info}/RECORD

@@ -1,5 +1,5 @@
 hdl/__init__.py,sha256=GffnD0jLJdhkd-vo989v40N90sQbofkayRBwxc6TVhQ,72
-hdl/_version.py,sha256=jeNdt9VGQNw1iIiYHVNvXMaEDEn4mkNvXMSVcAGw4fI,413
+hdl/_version.py,sha256=tr9Pq2sozjd5Ty_4lPM_A-i6XowDPOaB6nT_SLKjIE4,413
 hdl/args/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/args/loss_args.py,sha256=s7YzSdd7IjD24rZvvOrxLLFqMZQb9YylxKeyelSdrTk,70
 hdl/controllers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -131,12 +131,12 @@ hdl/utils/llm/chat.py,sha256=sk7Lw5Oa30k-l2fnJknkMmTc5zkBeEKsR981aeFhH5s,11907
 hdl/utils/llm/embs.py,sha256=Tf0FOYrOFZp7qQpEPiSCXzlgyHH0X9HVTUtsup74a9E,7174
 hdl/utils/llm/extract.py,sha256=2sK_WJzmYIc8iuWaM9DA6Nw3_6q1O4lJ5pKpcZo-bBA,6512
 hdl/utils/llm/llama_chat.py,sha256=watcHGOaz-bv3x-yDucYlGk5f8FiqfFhwWogrl334fk,4387
-hdl/utils/llm/vis.py,sha256=z1NNh1Xni3l7c8i9VZLphEDGlfQSn8g5wIA7wudUgps,6516
+hdl/utils/llm/vis.py,sha256=KVRM5iy5Br_ldr0H-QkppSHpPGjKlKzPHEamF7v94do,7609
 hdl/utils/schedulers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/utils/schedulers/norm_lr.py,sha256=bDwCmdEK-WkgxQMFBiMuchv8Mm7C0-GZJ6usm-PQk14,4461
 hdl/utils/weather/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/utils/weather/weather.py,sha256=k11o6wM15kF8b9NMlEfrg68ak-SfSYLN3nOOflFUv-I,4381
-hjxdl-0.1.64.dist-info/METADATA,sha256=0Oy9QnqLsIOqprs7XFD3nG0CMopv4OIhbdcQaV19RX4,880
-hjxdl-0.1.64.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-hjxdl-0.1.64.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
-hjxdl-0.1.64.dist-info/RECORD,,
+hjxdl-0.1.66.dist-info/METADATA,sha256=6iHh5yVtaR5Mw6WXZYT_iYuW6SYOxj0-JLuKeKS2ChU,903
+hjxdl-0.1.66.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+hjxdl-0.1.66.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
+hjxdl-0.1.66.dist-info/RECORD,,