github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-07 12:05:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

printing backends

Browse Source
This commit is contained in:
Sefik Ilkin Serengil 2020-02-13 10:13:11 +03:00 committed by GitHub
parent b7ed1897f5
commit 08d09421c4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
deepface/DeepFace.py
View File

@ -39,14 +39,17 @@ def verify(img1_path, img2_path
#------------------------- #-------------------------
if model_name == 'VGG-Face': if model_name == 'VGG-Face':
print("Using VGG-Face backend.")
model = VGGFace.loadModel() model = VGGFace.loadModel()
input_shape = (224, 224) input_shape = (224, 224)
elif model_name == 'OpenFace': elif model_name == 'OpenFace':
print("Using OpenFace backend.")
model = OpenFace.loadModel() model = OpenFace.loadModel()
input_shape = (96, 96) input_shape = (96, 96)
elif model_name == 'Facenet': elif model_name == 'Facenet':
print("Using Facenet backend.")
model = Facenet.loadModel() model = Facenet.loadModel()
input_shape = (160, 160) input_shape = (160, 160)
@ -69,10 +72,13 @@ def verify(img1_path, img2_path
#find distances between embeddings #find distances between embeddings
if distance_metric == 'cosine': if distance_metric == 'cosine':
print("Using cosine similarity")
distance = dst.findCosineDistance(img1_representation, img2_representation) distance = dst.findCosineDistance(img1_representation, img2_representation)
elif distance_metric == 'euclidean': elif distance_metric == 'euclidean':
print("Using euclidean distance")
distance = dst.findEuclideanDistance(img1_representation, img2_representation) distance = dst.findEuclideanDistance(img1_representation, img2_representation)
elif distance_metric == 'euclidean_l2': elif distance_metric == 'euclidean_l2':
print("Using euclidean distance l2 form")
distance = dst.findEuclideanDistance(dst.l2_normalize(img1_representation), dst.l2_normalize(img2_representation)) distance = dst.findEuclideanDistance(dst.l2_normalize(img1_representation), dst.l2_normalize(img2_representation))
#------------------------- #-------------------------