From 07a2d5bf627eecc1feaf307b7a7ef18852971511 Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Fri, 8 Mar 2024 12:01:31 +0000
Subject: [PATCH 1/6] enhancement for find function

- detect replaced files already in data store
- store column names in the pickle
---
 deepface/commons/package_utils.py |  16 +++++
 deepface/modules/recognition.py   | 111 +++++++++++++++++++-----------
 2 files changed, 88 insertions(+), 39 deletions(-)

diff --git a/deepface/commons/package_utils.py b/deepface/commons/package_utils.py
index 9326b94a3..2226e070c 100644
--- a/deepface/commons/package_utils.py
+++ b/deepface/commons/package_utils.py
@@ -1,3 +1,6 @@
+# built-in dependencies
+import hashlib
+
 # 3rd party dependencies
 import tensorflow as tf
 
@@ -14,3 +17,16 @@ def get_tf_major_version() -> int:
         major_version (int)
     """
     return int(tf.__version__.split(".", maxsplit=1)[0])
+
+
+def find_hash_of_file(file_path: str) -> str:
+    """
+    Find hash of image file
+    Args:
+        file_path (str): exact image path
+    Returns:
+        hash (str): digest with sha1 algorithm
+    """
+    with open(file_path, "rb") as f:
+        digest = hashlib.sha1(f.read()).hexdigest()
+    return digest
diff --git a/deepface/modules/recognition.py b/deepface/modules/recognition.py
index fa2b3b77f..b3a8a1132 100644
--- a/deepface/modules/recognition.py
+++ b/deepface/modules/recognition.py
@@ -1,7 +1,7 @@
 # built-in dependencies
 import os
 import pickle
-from typing import List, Union, Optional
+from typing import List, Union, Optional, Dict, Any
 import time
 
 # 3rd party dependencies
@@ -11,6 +11,7 @@
 
 # project dependencies
 from deepface.commons.logger import Logger
+from deepface.commons import package_utils
 from deepface.modules import representation, detection, modeling, verification
 from deepface.models.FacialRecognition import FacialRecognition
 
@@ -97,14 +98,16 @@ def find(
 
     # ---------------------------------------
 
-    file_name = f"representations_{model_name}.pkl"
-    file_name = file_name.replace("-", "_").lower()
+    file_name = f"ds_{model_name}_{detector_backend}_v2.pkl"
+    file_name = file_name.replace("-", "").lower()
     datastore_path = os.path.join(db_path, file_name)
     representations = []
 
+    # required columns for representations
     df_cols = [
         "identity",
-        f"{model_name}_representation",
+        "hash",
+        "embedding",
         "target_x",
         "target_y",
         "target_w",
@@ -120,14 +123,18 @@ def find(
     with open(datastore_path, "rb") as f:
         representations = pickle.load(f)
 
-    # Check if the representations are out-of-date
-    if len(representations) > 0:
-        if len(representations[0]) != len(df_cols):
+    # check each item of representations list has required keys
+    for i, current_representation in enumerate(representations):
+        missing_keys = list(set(df_cols) - set(current_representation.keys()))
+        if len(missing_keys) > 0:
             raise ValueError(
-                f"Seems existing {datastore_path} is out-of-the-date."
-                "Please delete it and re-run."
+                f"{i}-th item does not have some required keys - {missing_keys}."
+                f"Consider to delete {datastore_path}"
             )
-        pickled_images = [representation[0] for representation in representations]
+
+    # Check if the representations are out-of-date
+    if len(representations) > 0:
+        pickled_images = [representation["identity"] for representation in representations]
     else:
         pickled_images = []
 
@@ -136,19 +143,35 @@ def find(
 
     # 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
+    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 not silent and (len(new_images) > 0 or len(old_images) > 0):
         logger.info(f"Found {len(new_images)} new images and {len(old_images)} removed images")
 
+    # detect replaced images
+    replaced_images = []
+    for current_representation in representations:
+        identity = current_representation["identity"]
+        if identity in old_images:
+            continue
+        alpha_hash = current_representation["hash"]
+        beta_hash = package_utils.find_hash_of_file(identity)
+        if alpha_hash != beta_hash:
+            logger.warn(f"Even though {identity} represented before, it's replaced later.")
+            replaced_images.append(identity)
+
+    # append replaced images into both old and new images. these will be dropped and re-added.
+    new_images = new_images + replaced_images
+    old_images = old_images + replaced_images
+
     # remove old images first
-    if len(old_images)>0:
-        representations = [rep for rep in representations if rep[0] not in old_images]
+    if len(old_images) > 0:
+        representations = [rep for rep in representations if rep["identity"] not in old_images]
         must_save_pickle = True
 
     # find representations for new images
-    if len(new_images)>0:
+    if len(new_images) > 0:
         representations += __find_bulk_embeddings(
             employees=new_images,
             model_name=model_name,
@@ -158,7 +181,7 @@ def find(
             align=align,
             normalization=normalization,
             silent=silent,
-        ) # add new images
+        )  # add new images
         must_save_pickle = True
 
     if must_save_pickle:
@@ -176,10 +199,7 @@ def find(
 
     # ----------------------------
     # now, we got representations for facial database
-    df = pd.DataFrame(
-        representations,
-        columns=df_cols,
-    )
+    df = pd.DataFrame(representations)
 
     # img path might have more than once face
     source_objs = detection.extract_faces(
@@ -216,9 +236,9 @@ def find(
 
         distances = []
         for _, instance in df.iterrows():
-            source_representation = instance[f"{model_name}_representation"]
+            source_representation = instance["embedding"]
             if source_representation is None:
-                distances.append(float("inf")) # no representation for this image
+                distances.append(float("inf"))  # no representation for this image
                 continue
 
             target_dims = len(list(target_representation))
@@ -254,7 +274,7 @@ def find(
         result_df["threshold"] = target_threshold
         result_df["distance"] = distances
 
-        result_df = result_df.drop(columns=[f"{model_name}_representation"])
+        result_df = result_df.drop(columns=["embedding"])
         # pylint: disable=unsubscriptable-object
         result_df = result_df[result_df["distance"] <= target_threshold]
         result_df = result_df.sort_values(by=["distance"], ascending=True).reset_index(drop=True)
@@ -297,7 +317,7 @@ def __find_bulk_embeddings(
     expand_percentage: int = 0,
     normalization: str = "base",
     silent: bool = False,
-):
+) -> List[Dict["str", Any]]:
     """
     Find embeddings of a list of images
 
@@ -323,8 +343,8 @@ def __find_bulk_embeddings(
 
         silent (bool): enable or disable informative logging
     Returns:
-        representations (list): pivot list of embeddings with
-            image name and detected face area's coordinates
+        representations (list): pivot list of dict with
+            image name, hash, embedding and detected face area's coordinates
     """
     representations = []
     for employee in tqdm(
@@ -332,6 +352,8 @@ def __find_bulk_embeddings(
         desc="Finding representations",
         disable=silent,
     ):
+        file_hash = package_utils.find_hash_of_file(employee)
+
         try:
             img_objs = detection.extract_faces(
                 img_path=employee,
@@ -342,15 +364,23 @@ def __find_bulk_embeddings(
                 align=align,
                 expand_percentage=expand_percentage,
             )
+
         except ValueError as err:
-            logger.error(
-                f"Exception while extracting faces from {employee}: {str(err)}"
-            )
+            logger.error(f"Exception while extracting faces from {employee}: {str(err)}")
             img_objs = []
 
         if len(img_objs) == 0:
-            logger.warn(f"No face detected in {employee}. It will be skipped in detection.")
-            representations.append((employee, None, 0, 0, 0, 0))
+            representations.append(
+                {
+                    "identity": employee,
+                    "hash": file_hash,
+                    "embedding": None,
+                    "target_x": 0,
+                    "target_y": 0,
+                    "target_w": 0,
+                    "target_h": 0,
+                }
+            )
         else:
             for img_obj in img_objs:
                 img_content = img_obj["face"]
@@ -365,13 +395,16 @@ def __find_bulk_embeddings(
                 )
 
                 img_representation = embedding_obj[0]["embedding"]
-                representations.append((
-                    employee,
-                    img_representation,
-                    img_region["x"],
-                    img_region["y"],
-                    img_region["w"],
-                    img_region["h"]
-                    ))
+                representations.append(
+                    {
+                        "identity": employee,
+                        "hash": file_hash,
+                        "embedding": img_representation,
+                        "target_x": img_region["x"],
+                        "target_y": img_region["y"],
+                        "target_w": img_region["w"],
+                        "target_h": img_region["h"],
+                    }
+                )
 
     return representations

From 2f9f9761d0845f903eb054cbac8bb6ab0e9cfbc0 Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Fri, 8 Mar 2024 12:01:45 +0000
Subject: [PATCH 2/6] cover uppercase links

---
 deepface/modules/preprocessing.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/deepface/modules/preprocessing.py b/deepface/modules/preprocessing.py
index 42756c179..7daf248b5 100644
--- a/deepface/modules/preprocessing.py
+++ b/deepface/modules/preprocessing.py
@@ -34,7 +34,7 @@ def load_image(img: Union[str, np.ndarray]) -> Tuple[np.ndarray, str]:
         return load_base64(img), "base64 encoded string"
 
     # The image is a url
-    if img.startswith("http://") or img.startswith("https://"):
+    if img.lower().startswith("http://") or img.lower().startswith("https://"):
         return load_image_from_web(url=img), img
 
     # The image is a path

From d7c2998e1bdd021a321d588fcf37bd7fc49bf4dc Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Fri, 8 Mar 2024 13:55:02 +0000
Subject: [PATCH 3/6] wrapper for find distance added

---
 deepface/modules/recognition.py  | 18 +++-------------
 deepface/modules/verification.py | 37 +++++++++++++++++++++++---------
 2 files changed, 30 insertions(+), 25 deletions(-)

diff --git a/deepface/modules/recognition.py b/deepface/modules/recognition.py
index b3a8a1132..ed8b47b50 100644
--- a/deepface/modules/recognition.py
+++ b/deepface/modules/recognition.py
@@ -250,21 +250,9 @@ def find(
                     + " after pickle created. Delete the {file_name} and re-run."
                 )
 
-            if distance_metric == "cosine":
-                distance = verification.find_cosine_distance(
-                    source_representation, target_representation
-                )
-            elif distance_metric == "euclidean":
-                distance = verification.find_euclidean_distance(
-                    source_representation, target_representation
-                )
-            elif distance_metric == "euclidean_l2":
-                distance = verification.find_euclidean_distance(
-                    verification.l2_normalize(source_representation),
-                    verification.l2_normalize(target_representation),
-                )
-            else:
-                raise ValueError(f"invalid distance metric passes - {distance_metric}")
+            distance = verification.find_distance(
+                source_representation, target_representation, distance_metric
+            )
 
             distances.append(distance)
 
diff --git a/deepface/modules/verification.py b/deepface/modules/verification.py
index 300c2f99d..dc667138c 100644
--- a/deepface/modules/verification.py
+++ b/deepface/modules/verification.py
@@ -141,16 +141,7 @@ def verify(
     regions = []
     for idx, img1_embedding in enumerate(img1_embeddings):
         for idy, img2_embedding in enumerate(img2_embeddings):
-            if distance_metric == "cosine":
-                distance = find_cosine_distance(img1_embedding, img2_embedding)
-            elif distance_metric == "euclidean":
-                distance = find_euclidean_distance(img1_embedding, img2_embedding)
-            elif distance_metric == "euclidean_l2":
-                distance = find_euclidean_distance(
-                    l2_normalize(img1_embedding), l2_normalize(img2_embedding)
-                )
-            else:
-                raise ValueError("Invalid distance_metric passed - ", distance_metric)
+            distance = find_distance(img1_embedding, img2_embedding, distance_metric)
             distances.append(distance)
             regions.append((img1_objs[idx]["facial_area"], img2_objs[idy]["facial_area"]))
 
@@ -234,6 +225,32 @@ def l2_normalize(x: Union[np.ndarray, list]) -> np.ndarray:
     return x / np.sqrt(np.sum(np.multiply(x, x)))
 
 
+def find_distance(
+    alpha_embedding: Union[np.ndarray, list],
+    beta_embedding: Union[np.ndarray, list],
+    distance_metric: str,
+) -> np.float64:
+    """
+    Wrapper to find distance between vectors according to the given distance metric
+    Args:
+        source_representation (np.ndarray or list): 1st vector
+        test_representation (np.ndarray or list): 2nd vector
+    Returns
+        distance (np.float64): calculated cosine distance
+    """
+    if distance_metric == "cosine":
+        distance = find_cosine_distance(alpha_embedding, beta_embedding)
+    elif distance_metric == "euclidean":
+        distance = find_euclidean_distance(alpha_embedding, beta_embedding)
+    elif distance_metric == "euclidean_l2":
+        distance = find_euclidean_distance(
+            l2_normalize(alpha_embedding), l2_normalize(beta_embedding)
+        )
+    else:
+        raise ValueError("Invalid distance_metric passed - ", distance_metric)
+    return distance
+
+
 def find_threshold(model_name: str, distance_metric: str) -> float:
     """
     Retrieve pre-tuned threshold values for a model and distance metric pair

From 6eced68e699a044981d115f6734f085b17ce3a17 Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Fri, 8 Mar 2024 15:22:58 +0000
Subject: [PATCH 4/6] support embedding input for verify

---
 deepface/DeepFace.py             |   5 +
 deepface/modules/verification.py | 175 ++++++++++++++++++++++---------
 tests/test_verify.py             |  51 +++++++++
 3 files changed, 184 insertions(+), 47 deletions(-)

diff --git a/deepface/DeepFace.py b/deepface/DeepFace.py
index aafb297f5..e5e16cdaa 100644
--- a/deepface/DeepFace.py
+++ b/deepface/DeepFace.py
@@ -62,6 +62,7 @@ def verify(
     align: bool = True,
     expand_percentage: int = 0,
     normalization: str = "base",
+    silent: bool = False,
 ) -> Dict[str, Any]:
     """
     Verify if an image pair represents the same person or different persons.
@@ -91,6 +92,9 @@ def verify(
         normalization (string): Normalize the input image before feeding it to the model.
             Options: base, raw, Facenet, Facenet2018, VGGFace, VGGFace2, ArcFace (default is base)
 
+        silent (boolean): Suppress or allow some log messages for a quieter analysis process
+            (default is False).
+
     Returns:
         result (dict): A dictionary containing verification results with following keys.
 
@@ -126,6 +130,7 @@ def verify(
         align=align,
         expand_percentage=expand_percentage,
         normalization=normalization,
+        silent=silent,
     )
 
 
diff --git a/deepface/modules/verification.py b/deepface/modules/verification.py
index dc667138c..6ab55310a 100644
--- a/deepface/modules/verification.py
+++ b/deepface/modules/verification.py
@@ -1,6 +1,6 @@
 # built-in dependencies
 import time
-from typing import Any, Dict, Union
+from typing import Any, Dict, Union, List, Tuple
 
 # 3rd party dependencies
 import numpy as np
@@ -8,11 +8,14 @@
 # project dependencies
 from deepface.modules import representation, detection, modeling
 from deepface.models.FacialRecognition import FacialRecognition
+from deepface.commons.logger import Logger
+
+logger = Logger(module="deepface/modules/verification.py")
 
 
 def verify(
-    img1_path: Union[str, np.ndarray],
-    img2_path: Union[str, np.ndarray],
+    img1_path: Union[str, np.ndarray, List[float]],
+    img2_path: Union[str, np.ndarray, List[float]],
     model_name: str = "VGG-Face",
     detector_backend: str = "opencv",
     distance_metric: str = "cosine",
@@ -20,6 +23,7 @@ def verify(
     align: bool = True,
     expand_percentage: int = 0,
     normalization: str = "base",
+    silent: bool = False,
 ) -> Dict[str, Any]:
     """
     Verify if an image pair represents the same person or different persons.
@@ -30,10 +34,10 @@ def verify(
 
     Args:
         img1_path (str or np.ndarray): Path to the first image. Accepts exact image path
-            as a string, numpy array (BGR), or base64 encoded images.
+            as a string, numpy array (BGR), base64 encoded images or pre-calculated embeddings.
 
         img2_path (str or np.ndarray): Path to the second image. Accepts exact image path
-            as a string, numpy array (BGR), or base64 encoded images.
+            as a string, numpy array (BGR), base64 encoded images or pre-calculated embeddings.
 
         model_name (str): Model for face recognition. Options: VGG-Face, Facenet, Facenet512,
             OpenFace, DeepFace, DeepID, Dlib, ArcFace and SFace (default is VGG-Face).
@@ -54,6 +58,9 @@ def verify(
         normalization (string): Normalize the input image before feeding it to the model.
             Options: base, raw, Facenet, Facenet2018, VGGFace, VGGFace2, ArcFace (default is base)
 
+        silent (boolean): Suppress or allow some log messages for a quieter analysis process
+            (default is False).
+
     Returns:
         result (dict): A dictionary containing verification results.
 
@@ -81,74 +88,96 @@ def verify(
 
     tic = time.time()
 
-    # --------------------------------
     model: FacialRecognition = modeling.build_model(model_name)
-    target_size = model.input_shape
-
-    try:
-        img1_objs = detection.extract_faces(
+    dims = model.output_shape
+
+    if isinstance(img1_path, list):
+        # given image is already pre-calculated embedding
+        if not all(isinstance(dim, float) for dim in img1_path):
+            raise ValueError(
+                "When passing img1_path as a list, ensure that all its items are of type float."
+            )
+
+        if silent is False:
+            logger.warn(
+                "You passed 1st image as pre-calculated embeddings."
+                f"Please ensure that embeddings have been calculated for the {model_name} model."
+            )
+
+        if len(img1_path) != dims:
+            raise ValueError(
+                f"embeddings of {model_name} should have {dims} dimensions,"
+                f" but it has {len(img1_path)} dimensions input"
+            )
+
+        img1_embeddings = [img1_path]
+        img1_facial_areas = [None]
+    else:
+        img1_embeddings, img1_facial_areas = __extract_faces_and_embeddings(
             img_path=img1_path,
-            target_size=target_size,
+            model_name=model_name,
             detector_backend=detector_backend,
-            grayscale=False,
             enforce_detection=enforce_detection,
             align=align,
             expand_percentage=expand_percentage,
+            normalization=normalization,
         )
-    except ValueError as err:
-        raise ValueError("Exception while processing img1_path") from err
 
-    try:
-        img2_objs = detection.extract_faces(
+    if isinstance(img2_path, list):
+        # given image is already pre-calculated embedding
+        if not all(isinstance(dim, float) for dim in img2_path):
+            raise ValueError(
+                "When passing img2_path as a list, ensure that all its items are of type float."
+            )
+
+        if silent is False:
+            logger.warn(
+                "You passed 2nd image as pre-calculated embeddings."
+                f"Please ensure that embeddings have been calculated for the {model_name} model."
+            )
+
+        if len(img2_path) != dims:
+            raise ValueError(
+                f"embeddings of {model_name} should have {dims} dimensions,"
+                f" but it has {len(img2_path)} dimensions input"
+            )
+
+        img2_embeddings = [img2_path]
+        img2_facial_areas = [None]
+    else:
+        img2_embeddings, img2_facial_areas = __extract_faces_and_embeddings(
             img_path=img2_path,
-            target_size=target_size,
+            model_name=model_name,
             detector_backend=detector_backend,
-            grayscale=False,
             enforce_detection=enforce_detection,
             align=align,
             expand_percentage=expand_percentage,
-        )
-    except ValueError as err:
-        raise ValueError("Exception while processing img2_path") from err
-
-    img1_embeddings = []
-    for img1_obj in img1_objs:
-        img1_embedding_obj = representation.represent(
-            img_path=img1_obj["face"],
-            model_name=model_name,
-            enforce_detection=enforce_detection,
-            detector_backend="skip",
-            align=align,
             normalization=normalization,
         )
-        img1_embedding = img1_embedding_obj[0]["embedding"]
-        img1_embeddings.append(img1_embedding)
 
-    img2_embeddings = []
-    for img2_obj in img2_objs:
-        img2_embedding_obj = representation.represent(
-            img_path=img2_obj["face"],
-            model_name=model_name,
-            enforce_detection=enforce_detection,
-            detector_backend="skip",
-            align=align,
-            normalization=normalization,
-        )
-        img2_embedding = img2_embedding_obj[0]["embedding"]
-        img2_embeddings.append(img2_embedding)
+    no_facial_area = {
+        "x": None,
+        "y": None,
+        "w": None,
+        "h": None,
+        "left_eye": None,
+        "right_eye": None,
+    }
 
     distances = []
-    regions = []
+    facial_areas = []
     for idx, img1_embedding in enumerate(img1_embeddings):
         for idy, img2_embedding in enumerate(img2_embeddings):
             distance = find_distance(img1_embedding, img2_embedding, distance_metric)
             distances.append(distance)
-            regions.append((img1_objs[idx]["facial_area"], img2_objs[idy]["facial_area"]))
+            facial_areas.append(
+                (img1_facial_areas[idx] or no_facial_area, img2_facial_areas[idy] or no_facial_area)
+            )
 
     # find the face pair with minimum distance
     threshold = find_threshold(model_name, distance_metric)
     distance = float(min(distances))  # best distance
-    facial_areas = regions[np.argmin(distances)]
+    facial_areas = facial_areas[np.argmin(distances)]
 
     toc = time.time()
 
@@ -166,6 +195,58 @@ def verify(
     return resp_obj
 
 
+def __extract_faces_and_embeddings(
+    img_path: Union[str, np.ndarray],
+    model_name: str = "VGG-Face",
+    detector_backend: str = "opencv",
+    enforce_detection: bool = True,
+    align: bool = True,
+    expand_percentage: int = 0,
+    normalization: str = "base",
+) -> Tuple[List[List[float]], List[dict]]:
+    """
+    Extract facial areas and find corresponding embeddings for given image
+    Returns:
+        embeddings (List[float])
+        facial areas (List[dict])
+    """
+    embeddings = []
+    facial_areas = []
+
+    model: FacialRecognition = modeling.build_model(model_name)
+    target_size = model.input_shape
+
+    try:
+        img_objs = detection.extract_faces(
+            img_path=img_path,
+            target_size=target_size,
+            detector_backend=detector_backend,
+            grayscale=False,
+            enforce_detection=enforce_detection,
+            align=align,
+            expand_percentage=expand_percentage,
+        )
+    except ValueError as err:
+        raise ValueError("Exception while processing img1_path") from err
+
+    # find embeddings for each face
+    for img_obj in img_objs:
+        img_embedding_obj = representation.represent(
+            img_path=img_obj["face"],
+            model_name=model_name,
+            enforce_detection=enforce_detection,
+            detector_backend="skip",
+            align=align,
+            normalization=normalization,
+        )
+        # already extracted face given, safe to access its 1st item
+        img_embedding = img_embedding_obj[0]["embedding"]
+        embeddings.append(img_embedding)
+        facial_areas.append(img_obj["facial_area"])
+
+    return embeddings, facial_areas
+
+
 def find_cosine_distance(
     source_representation: Union[np.ndarray, list], test_representation: Union[np.ndarray, list]
 ) -> np.float64:
diff --git a/tests/test_verify.py b/tests/test_verify.py
index 5d135417c..ff1f9fdfd 100644
--- a/tests/test_verify.py
+++ b/tests/test_verify.py
@@ -1,3 +1,4 @@
+import pytest
 import cv2
 from deepface import DeepFace
 from deepface.commons.logger import Logger
@@ -100,3 +101,53 @@ def test_verify_for_preloaded_image():
     res = DeepFace.verify(img1, img2)
     assert res["verified"] is True
     logger.info("✅ test verify for pre-loaded image done")
+
+
+def test_verify_for_precalculated_embeddings():
+    model_name = "Facenet"
+
+    img1_path = "dataset/img1.jpg"
+    img2_path = "dataset/img2.jpg"
+
+    img1_embedding = DeepFace.represent(img_path=img1_path, model_name=model_name)[0]["embedding"]
+    img2_embedding = DeepFace.represent(img_path=img2_path, model_name=model_name)[0]["embedding"]
+
+    result = DeepFace.verify(
+        img1_path=img1_embedding, img2_path=img2_embedding, model_name=model_name, silent=True
+    )
+
+    assert result["verified"] is True
+    assert result["distance"] < result["threshold"]
+    assert result["model"] == model_name
+
+    logger.info("✅ test verify for pre-calculated embeddings done")
+
+
+def test_verify_with_precalculated_embeddings_for_incorrect_model():
+    # generate embeddings with VGG (default)
+    img1_path = "dataset/img1.jpg"
+    img2_path = "dataset/img2.jpg"
+    img1_embedding = DeepFace.represent(img_path=img1_path)[0]["embedding"]
+    img2_embedding = DeepFace.represent(img_path=img2_path)[0]["embedding"]
+
+    with pytest.raises(
+        ValueError,
+        match="embeddings of Facenet should have 128 dimensions, but it has 4096 dimensions input",
+    ):
+        _ = DeepFace.verify(
+            img1_path=img1_embedding, img2_path=img2_embedding, model_name="Facenet", silent=True
+        )
+
+    logger.info("✅ test verify with pre-calculated embeddings for incorrect model done")
+
+
+def test_verify_for_broken_embeddings():
+    img1_embeddings = ["a", "b", "c"]
+    img2_embeddings = [1, 2, 3]
+
+    with pytest.raises(
+        ValueError,
+        match="When passing img1_path as a list, ensure that all its items are of type float.",
+    ):
+        _ = DeepFace.verify(img1_path=img1_embeddings, img2_path=img2_embeddings)
+    logger.info("✅ test verify for broken embeddings content is done")

From b3c98e3b1f4f616eeca6910dd779d33015e4623a Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Fri, 8 Mar 2024 16:14:09 +0000
Subject: [PATCH 5/6] details for contribution

---
 README.md | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index d0ea40a4a..317cbec23 100644
--- a/README.md
+++ b/README.md
@@ -312,9 +312,11 @@ $ deepface analyze -img_path tests/dataset/img1.jpg
 
 You can also run these commands if you are running deepface with docker. Please follow the instructions in the [shell script](https://github.com/serengil/deepface/blob/master/scripts/dockerize.sh#L17).
 
-## Contribution [![Tests](https://github.com/serengil/deepface/actions/workflows/tests.yml/badge.svg)](https://github.com/serengil/deepface/actions/workflows/tests.yml)
+## Contribution
 
-Pull requests are more than welcome! You should run the unit tests and linting locally by running `make test && make lint` before creating a PR. Once a PR sent, GitHub test workflow will be run automatically and unit test results will be available in [GitHub actions](https://github.com/serengil/deepface/actions) before approval. Besides, workflow will evaluate the code with pylint as well.
+Pull requests are more than welcome! If you are planning to contribute a large patch, please create an issue first to get any upfront questions or design decisions out of the way first.
+
+Before creating a PR, you should run the unit tests and linting locally by running `make test && make lint` command. Once a PR sent, GitHub test workflow will be run automatically and unit test and linting jobs will be available in [GitHub actions](https://github.com/serengil/deepface/actions) before approval.
 
 ## Support
 

From 259add4a13ca9ca282025e6690955fa874044455 Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Fri, 8 Mar 2024 19:52:38 +0000
Subject: [PATCH 6/6] simplify getting pickled images

---
 deepface/modules/recognition.py | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/deepface/modules/recognition.py b/deepface/modules/recognition.py
index ed8b47b50..dcc5abc2d 100644
--- a/deepface/modules/recognition.py
+++ b/deepface/modules/recognition.py
@@ -132,23 +132,20 @@ def find(
                 f"Consider to delete {datastore_path}"
             )
 
-    # Check if the representations are out-of-date
-    if len(representations) > 0:
-        pickled_images = [representation["identity"] for representation in representations]
-    else:
-        pickled_images = []
+    # embedded images
+    pickled_images = [representation["identity"] for representation in representations]
 
     # Get the list of images on storage
     storage_images = __list_images(path=db_path)
 
+    if len(storage_images) == 0:
+        raise ValueError(f"No item found in {db_path}")
+
     # 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 not silent and (len(new_images) > 0 or len(old_images) > 0):
-        logger.info(f"Found {len(new_images)} new images and {len(old_images)} removed images")
-
     # detect replaced images
     replaced_images = []
     for current_representation in representations:
@@ -158,9 +155,16 @@ def find(
         alpha_hash = current_representation["hash"]
         beta_hash = package_utils.find_hash_of_file(identity)
         if alpha_hash != beta_hash:
-            logger.warn(f"Even though {identity} represented before, it's replaced later.")
+            logger.debug(f"Even though {identity} represented before, it's replaced later.")
             replaced_images.append(identity)
 
+    if not silent and (len(new_images) > 0 or len(old_images) > 0 or len(replaced_images) > 0):
+        logger.info(
+            f"Found {len(new_images)} newly added image(s)"
+            f", {len(old_images)} removed image(s)"
+            f", {len(replaced_images)} replaced image(s)."
+        )
+
     # append replaced images into both old and new images. these will be dropped and re-added.
     new_images = new_images + replaced_images
     old_images = old_images + replaced_images
@@ -201,6 +205,9 @@ def find(
     # now, we got representations for facial database
     df = pd.DataFrame(representations)
 
+    if silent is False:
+        logger.info(f"Searching {img_path} in {df.shape[0]} length datastore")
+
     # img path might have more than once face
     source_objs = detection.extract_faces(
         img_path=img_path,