Simplify find data initialization

deepface/modules/recognition.py

@@ -100,6 +100,7 @@ def find(
     file_name = f"representations_{model_name}.pkl"
     file_name = file_name.replace("-", "_").lower()
     datastore_path = os.path.join(db_path, file_name)
+    representations = []
 
     df_cols = [
         "identity",
@@ -110,29 +111,48 @@ def find(
         "target_h",
     ]
 
-    if os.path.exists(datastore_path):
+    # Ensure the proper pickle file exists
+    if not os.path.exists(datastore_path):
+        with open(datastore_path, "wb") as f:
+            pickle.dump([], f)
+            f.close()
+
+    # Load the representations from the pickle file
     with open(datastore_path, "rb") as f:
         representations = pickle.load(f)
+        f.close()
 
-            if len(representations) > 0 and len(representations[0]) != len(df_cols):
+    # Check if the representations are out-of-date
+    if len(representations) > 0:
+        if len(representations[0]) != len(df_cols):
             raise ValueError(
                 f"Seems existing {datastore_path} is out-of-the-date."
                 "Please delete it and re-run."
             )
+        pickled_images = [representation[0] for representation in representations]
+    else:
+        pickled_images = []
 
-        alpha_employees = __list_images(path=db_path)
-        beta_employees = [representation[0] for representation in representations]
+    # Get the list of images on storage
+    storage_images = __list_images(path=db_path)
 
-        newbies = list(set(alpha_employees) - set(beta_employees))
-        oldies = list(set(beta_employees) - set(alpha_employees))
+    # Enforce data consistency amongst on disk images and pickle file
+    must_save_pickle = False
+    new_images = list(set(storage_images) - set(pickled_images)) # images added to storage
+    old_images = list(set(pickled_images) - set(storage_images)) # images removed from storage
 
-        if newbies:
-            logger.warn(
-                f"Items {newbies} were added into {db_path}"
-                f" just after data source {datastore_path} created!"
-            )
-            newbies_representations = __find_bulk_embeddings(
-                employees=newbies,
+    if not silent:
+        logger.info(f"Found {len(new_images)} new images and {len(old_images)} removed images")
+
+    # remove old images first
+    if len(old_images)>0:
+        representations = [rep for rep in representations if rep[0] not in old_images]
+        must_save_pickle = True
+
+    # find representations for new images
+    if len(new_images)>0:
+        representations += __find_bulk_embeddings(
+            employees=new_images,
             model_name=model_name,
             target_size=target_size,
             detector_backend=detector_backend,
@@ -140,63 +160,22 @@ def find(
             align=align,
             normalization=normalization,
             silent=silent,
-            )
-            representations = representations + newbies_representations
+        ) # add new images
+        must_save_pickle = True
 
-        if oldies:
-            logger.warn(
-                f"Items {oldies} were dropped from {db_path}"
-                f" just after data source {datastore_path} created!"
-            )
-            representations = [rep for rep in representations if rep[0] not in oldies]
+    if must_save_pickle:
+        with open(datastore_path, "wb") as f:
+            pickle.dump(representations, f)
+            f.close()
+        if not silent:
+            logger.info(f"There are now {len(representations)} representations in {file_name}")
 
-        if newbies or oldies:
+    # Should we have no representations bailout
     if len(representations) == 0:
-                raise ValueError(f"There is no image in {db_path} anymore!")
-
-            # save new representations
-            with open(datastore_path, "wb") as f:
-                pickle.dump(representations, f)
-
+        toc = time.time()
         if not silent:
-                logger.info(
-                    f"{len(newbies)} new representations are just added"
-                    f" whereas {len(oldies)} represented one(s) are just dropped"
-                    f" in {os.path.join(db_path,file_name)} file."
-                )
-
-        if not silent:
-            logger.info(f"There are {len(representations)} representations found in {file_name}")
-
-    else:  # create representation.pkl from scratch
-        employees = __list_images(path=db_path)
-
-        if len(employees) == 0:
-            raise ValueError(
-                f"Could not find any valid image in {db_path} folder!"
-                "Valid images are .jpg, .jpeg or .png files.",
-            )
-
-        # ------------------------
-        # find representations for db images
-        representations = __find_bulk_embeddings(
-            employees=employees,
-            model_name=model_name,
-            target_size=target_size,
-            detector_backend=detector_backend,
-            enforce_detection=enforce_detection,
-            align=align,
-            normalization=normalization,
-            silent=silent,
-        )
-
-        # -------------------------------
-
-        with open(datastore_path, "wb") as f:
-            pickle.dump(representations, f)
-
-        if not silent:
-            logger.info(f"Representations stored in {datastore_path} file.")
+            logger.info(f"find function duration {toc - tic} seconds")
+        return []
 
     # ----------------------------
     # now, we got representations for facial database
@@ -290,7 +269,7 @@ def find(
     toc = time.time()
 
     if not silent:
-        logger.info(f"find function lasts {toc - tic} seconds")
+        logger.info(f"find function duration {toc - tic} seconds")
 
     return resp_obj