github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-07 20:15:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

avoid multiple feature extraction for faces in image pairs

Browse Source
This commit is contained in:
Sefik Ilkin Serengil 2024-03-02 20:20:33 +00:00
parent 715d6317d4
commit e70496ba6f
1 changed files with 35 additions and 37 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

72
deepface/modules/verification.py
View File

@ -110,61 +110,59 @@ def verify(
) )
except ValueError as err: except ValueError as err:
raise ValueError("Exception while processing img2_path") from 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)
distances = [] distances = []
regions = [] regions = []
# now we will find the face pair with minimum distance for idx, img1_embedding in enumerate(img1_embeddings):
for img1_obj in img1_objs: for idy, img2_embedding in enumerate(img2_embeddings):
img1_content = img1_obj["face"]
img1_region = img1_obj["facial_area"]
for img2_obj in img2_objs:
img2_content = img2_obj["face"]
img2_region = img2_obj["facial_area"]
img1_embedding_obj = representation.represent(
img_path=img1_content,
model_name=model_name,
enforce_detection=enforce_detection,
detector_backend="skip",
align=align,
normalization=normalization,
)
img2_embedding_obj = representation.represent(
img_path=img2_content,
model_name=model_name,
enforce_detection=enforce_detection,
detector_backend="skip",
align=align,
normalization=normalization,
)
img1_representation = img1_embedding_obj[0]["embedding"]
img2_representation = img2_embedding_obj[0]["embedding"]
if distance_metric == "cosine": if distance_metric == "cosine":
distance = find_cosine_distance(img1_representation, img2_representation) distance = find_cosine_distance(img1_embedding, img2_embedding)
elif distance_metric == "euclidean": elif distance_metric == "euclidean":
distance = find_euclidean_distance(img1_representation, img2_representation) distance = find_euclidean_distance(img1_embedding, img2_embedding)
elif distance_metric == "euclidean_l2": elif distance_metric == "euclidean_l2":
distance = find_euclidean_distance( distance = find_euclidean_distance(
l2_normalize(img1_representation), l2_normalize(img2_representation) l2_normalize(img1_embedding), l2_normalize(img2_embedding)
) )
else: else:
raise ValueError("Invalid distance_metric passed - ", distance_metric) raise ValueError("Invalid distance_metric passed - ", distance_metric)
distances.append(distance) distances.append(distance)
regions.append((img1_region, img2_region)) regions.append((img1_objs[idx]["facial_area"], img2_objs[idy]["facial_area"]))
# ------------------------------- # find the face pair with minimum distance
threshold = find_threshold(model_name, distance_metric) threshold = find_threshold(model_name, distance_metric)
distance = min(distances) # best distance distance = min(distances) # best distance
facial_areas = regions[np.argmin(distances)] facial_areas = regions[np.argmin(distances)]
toc = time.time() toc = time.time()
# pylint: disable=simplifiable-if-expression
resp_obj = { resp_obj = {
"verified": True if distance <= threshold else False, "verified": distance <= threshold,
"distance": distance, "distance": distance,
"threshold": threshold, "threshold": threshold,
"model": model_name, "model": model_name,