github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-08 20:45:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

represent function referenced in verify

Browse Source
This commit is contained in:
Sefik Ilkin Serengil 2021-04-11 14:19:33 +03:00
parent badc4d4dc6
commit 45b4714f47
1 changed files with 15 additions and 50 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
deepface/DeepFace.py
View File

@ -139,28 +139,14 @@ def verify(img1_path, img2_path = '', model_name = 'VGG-Face', distance_metric =
for i in model_names: for i in model_names:
custom_model = models[i] custom_model = models[i]
#decide input shape #img_path, model_name = 'VGG-Face', model = None, enforce_detection = True, detector_backend = 'mtcnn'
input_shape = functions.find_input_shape(custom_model) img1_representation = represent(img_path = img1_path
input_shape_x = input_shape[0]; input_shape_y = input_shape[1] , model_name = model_name, model = custom_model
, enforce_detection = enforce_detection, detector_backend = detector_backend)
#---------------------- img2_representation = represent(img_path = img2_path
#detect and align faces , model_name = model_name, model = custom_model
, enforce_detection = enforce_detection, detector_backend = detector_backend)
img1 = functions.preprocess_face(img=img1_path
, target_size=(input_shape_y, input_shape_x)
, enforce_detection = enforce_detection
, detector_backend = detector_backend)
img2 = functions.preprocess_face(img=img2_path
, target_size=(input_shape_y, input_shape_x)
, enforce_detection = enforce_detection
, detector_backend = detector_backend)
#----------------------
#find embeddings
img1_representation = custom_model.predict(img1)[0,:]
img2_representation = custom_model.predict(img2)[0,:]
#---------------------- #----------------------
#find distances between embeddings #find distances between embeddings
@ -570,20 +556,10 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
for j in model_names: for j in model_names:
custom_model = models[j] custom_model = models[j]
#---------------------------------- representation = represent(img_path = employee
#decide input shape , model_name = model_name, model = custom_model
, enforce_detection = enforce_detection, detector_backend = detector_backend)
input_shape = functions.find_input_shape(custom_model)
input_shape_x = input_shape[0]; input_shape_y = input_shape[1]
#----------------------------------
img = functions.preprocess_face(img = employee
, target_size = (input_shape_y, input_shape_x)
, enforce_detection = enforce_detection
, detector_backend = detector_backend)
representation = custom_model.predict(img)[0,:]
instance.append(representation) instance.append(representation)
#------------------------------- #-------------------------------
@ -620,19 +596,10 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
for j in model_names: for j in model_names:
custom_model = models[j] custom_model = models[j]
#-------------------------------- target_representation = represent(img_path = img_path
#decide input shape , model_name = model_name, model = custom_model
input_shape = functions.find_input_shape(custom_model) , enforce_detection = enforce_detection, detector_backend =detector_backend)
input_shape_x = input_shape[0]; input_shape_y = input_shape[1]
#--------------------------------
img = functions.preprocess_face(img = img_path, target_size = (input_shape_y, input_shape_x)
, enforce_detection = enforce_detection
, detector_backend = detector_backend)
target_representation = custom_model.predict(img)[0,:]
for k in metric_names: for k in metric_names:
distances = [] distances = []
@ -723,7 +690,7 @@ def find(img_path, db_path, model_name ='VGG-Face', distance_metric = 'cosine',
return None return None
def represent(img_path, model_name = 'VGG-Face', distance_metric = 'euclidean', model = None, enforce_detection = True, detector_backend = 'mtcnn'): def represent(img_path, model_name = 'VGG-Face', model = None, enforce_detection = True, detector_backend = 'mtcnn'):
""" """
This function represents facial images as vectors. This function represents facial images as vectors.
@ -733,8 +700,6 @@ def represent(img_path, model_name = 'VGG-Face', distance_metric = 'euclidean',
model_name (string): VGG-Face, Facenet, OpenFace, DeepFace, DeepID, Dlib, ArcFace. model_name (string): VGG-Face, Facenet, OpenFace, DeepFace, DeepID, Dlib, ArcFace.
distance_metric (string): cosine, euclidean, euclidean_l2
model: Built deepface model. A face recognition model is built every call of verify function. You can pass pre-built face recognition model optionally if you will call verify function several times. Consider to pass model if you are going to call represent function in a for loop. model: Built deepface model. A face recognition model is built every call of verify function. You can pass pre-built face recognition model optionally if you will call verify function several times. Consider to pass model if you are going to call represent function in a for loop.
model = DeepFace.build_model('VGG-Face') model = DeepFace.build_model('VGG-Face')