diff --git a/README.md b/README.md index ac4a8ea..d50a97a 100644 --- a/README.md +++ b/README.md @@ -16,7 +16,7 @@

-Deepface is a lightweight [face recognition](https://sefiks.com/2018/08/06/deep-face-recognition-with-keras/) and facial attribute analysis ([age](https://sefiks.com/2019/02/13/apparent-age-and-gender-prediction-in-keras/), [gender](https://sefiks.com/2019/02/13/apparent-age-and-gender-prediction-in-keras/), [emotion](https://sefiks.com/2018/01/01/facial-expression-recognition-with-keras/) and [race](https://sefiks.com/2019/11/11/race-and-ethnicity-prediction-in-keras/)) framework for python. It is a hybrid face recognition framework wrapping **state-of-the-art** models: [`VGG-Face`](https://sefiks.com/2018/08/06/deep-face-recognition-with-keras/), [`Google FaceNet`](https://sefiks.com/2018/09/03/face-recognition-with-facenet-in-keras/), [`OpenFace`](https://sefiks.com/2019/07/21/face-recognition-with-openface-in-keras/), [`Facebook DeepFace`](https://sefiks.com/2020/02/17/face-recognition-with-facebook-deepface-in-keras/), [`DeepID`](https://sefiks.com/2020/06/16/face-recognition-with-deepid-in-keras/), [`ArcFace`](https://sefiks.com/2020/12/14/deep-face-recognition-with-arcface-in-keras-and-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/) and SFace. +Deepface is a lightweight [face recognition](https://sefiks.com/2018/08/06/deep-face-recognition-with-keras/) and facial attribute analysis ([age](https://sefiks.com/2019/02/13/apparent-age-and-gender-prediction-in-keras/), [gender](https://sefiks.com/2019/02/13/apparent-age-and-gender-prediction-in-keras/), [emotion](https://sefiks.com/2018/01/01/facial-expression-recognition-with-keras/) and [race](https://sefiks.com/2019/11/11/race-and-ethnicity-prediction-in-keras/)) framework for python. It is a hybrid face recognition framework wrapping **state-of-the-art** models: [`VGG-Face`](https://sefiks.com/2018/08/06/deep-face-recognition-with-keras/), [`Google FaceNet`](https://sefiks.com/2018/09/03/face-recognition-with-facenet-in-keras/), [`OpenFace`](https://sefiks.com/2019/07/21/face-recognition-with-openface-in-keras/), [`Facebook DeepFace`](https://sefiks.com/2020/02/17/face-recognition-with-facebook-deepface-in-keras/), [`DeepID`](https://sefiks.com/2020/06/16/face-recognition-with-deepid-in-keras/), [`ArcFace`](https://sefiks.com/2020/12/14/deep-face-recognition-with-arcface-in-keras-and-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/) and `SFace`. Experiments show that human beings have 97.53% accuracy on facial recognition tasks whereas those models already reached and passed that accuracy level. @@ -60,7 +60,7 @@ df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db") **Face recognition models** - [`Demo`](https://youtu.be/i_MOwvhbLdI) -Deepface is a **hybrid** face recognition package. It currently wraps many **state-of-the-art** face recognition models: [`VGG-Face`](https://sefiks.com/2018/08/06/deep-face-recognition-with-keras/) , [`Google FaceNet`](https://sefiks.com/2018/09/03/face-recognition-with-facenet-in-keras/), [`OpenFace`](https://sefiks.com/2019/07/21/face-recognition-with-openface-in-keras/), [`Facebook DeepFace`](https://sefiks.com/2020/02/17/face-recognition-with-facebook-deepface-in-keras/), [`DeepID`](https://sefiks.com/2020/06/16/face-recognition-with-deepid-in-keras/), [`ArcFace`](https://sefiks.com/2020/12/14/deep-face-recognition-with-arcface-in-keras-and-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/) and SFace. The default configuration uses VGG-Face model. +Deepface is a **hybrid** face recognition package. It currently wraps many **state-of-the-art** face recognition models: [`VGG-Face`](https://sefiks.com/2018/08/06/deep-face-recognition-with-keras/) , [`Google FaceNet`](https://sefiks.com/2018/09/03/face-recognition-with-facenet-in-keras/), [`OpenFace`](https://sefiks.com/2019/07/21/face-recognition-with-openface-in-keras/), [`Facebook DeepFace`](https://sefiks.com/2020/02/17/face-recognition-with-facebook-deepface-in-keras/), [`DeepID`](https://sefiks.com/2020/06/16/face-recognition-with-deepid-in-keras/), [`ArcFace`](https://sefiks.com/2020/12/14/deep-face-recognition-with-arcface-in-keras-and-python/), [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/) and `SFace`. The default configuration uses VGG-Face model. ```python models = ["VGG-Face", "Facenet", "Facenet512", "OpenFace", "DeepFace", "DeepID", "ArcFace", "Dlib", "SFace"] @@ -190,7 +190,7 @@ Face recognition, facial attribute analysis and vector representation functions **Command Line Interface** -DeepFace comes with a command line interface as well. You are able to access its functions in command line in the command line as shown below. It expects the function name as 1st argument and functions arguments respectively. +DeepFace comes with a command line interface as well. You are able to access its functions in command line in the command line as shown below. It expects the function name as 1st argument and function arguments respectively. ```shell deepface verify -img1_path tests/dataset/img1.jpg -img2_path tests/dataset/img2.jpg diff --git a/deepface/basemodels/SFaceWrapper.py b/deepface/basemodels/SFaceWrapper.py index 2cca4a1..55eb3eb 100644 --- a/deepface/basemodels/SFaceWrapper.py +++ b/deepface/basemodels/SFaceWrapper.py @@ -6,12 +6,9 @@ import gdown from deepface.commons import functions -_url = "https://github.com/opencv/opencv_zoo/raw/master/models/face_recognition_sface/face_recognition_sface_2021dec.onnx" - - class _Layer: input_shape = (None, 112, 112, 3) - + output_shape = (None, 1, 128) class SFace: def __init__(self, model_path, backend_id=0, target_id=0): @@ -42,7 +39,7 @@ class SFace: return features -def load_model(*args, **kwargs): +def load_model(url = "https://github.com/opencv/opencv_zoo/raw/master/models/face_recognition_sface/face_recognition_sface_2021dec.onnx", *args, **kwargs): home = functions.get_deepface_home() file_name = home + '/.deepface/weights/face_recognition_sface_2021dec.onnx' @@ -50,7 +47,7 @@ def load_model(*args, **kwargs): print("sface weights will be downloaded...") output = file_name - gdown.download(_url, output, quiet=False) + gdown.download(url, output, quiet=False) model = SFace(file_name, 0, 0) return model diff --git a/tests/unit_tests.py b/tests/unit_tests.py index 073ef74..c83e065 100644 --- a/tests/unit_tests.py +++ b/tests/unit_tests.py @@ -194,9 +194,8 @@ dataset = [ ] #models = ['VGG-Face', 'Facenet', 'OpenFace', 'DeepFace', 'DeepID', 'Dlib', 'ArcFace'] +models = ['VGG-Face', 'Facenet', 'Facenet512', 'ArcFace', 'SFace'] #those are robust models metrics = ['cosine', 'euclidean', 'euclidean_l2'] -models = ['VGG-Face', 'Facenet', 'Facenet512', 'ArcFace'] #those are robust models -#metrics = ['cosine'] passed_tests = 0; test_cases = 0