deepface：适用于Python的轻量级深脸识别和面部属性分析（年龄，性别，情感和种族）框架

# deepface [](https://pepy.tech/project/deepface) [](https://github.com/serengil/deepface/blob/master/LICENSE) <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/deepface-icon-labeled.png" width="200" height="240"></p> 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/) and [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/). The library is mainly based on Keras and TensorFlow. ## Installation The easiest way to install deepface is to download it from [`PyPI`](https://pypi.org/project/deepface/). ```python pip install deepface ``` ## Face Recognition A modern [**face recognition pipeline**](https://sefiks.com/2020/05/01/a-gentle-introduction-to-face-recognition-in-deep-learning/) consists of 4 common stages: [detect](https://sefiks.com/2020/08/25/deep-face-detection-with-opencv-in-python/), [align](https://sefiks.com/2020/02/23/face-alignment-for-face-recognition-in-python-within-opencv/), [represent](https://sefiks.com/2018/08/06/deep-face-recognition-with-keras/) and [verify](https://sefiks.com/2020/05/22/fine-tuning-the-threshold-in-face-recognition/). Deepface handles all these common stages in the background. You can just call its verification, find or analysis function in its interface with a single line of code. **Face Verification** - [`Demo`](https://youtu.be/KRCvkNCOphE) Verification function under the deepface interface offers to verify face pairs as same person or different persons. You should pass face pairs as array instead of calling verify function in a for loop for the best practice. This will speed the function up dramatically and reduce the allocated memory. ```python from deepface import DeepFace result = DeepFace.verify("img1.jpg", "img2.jpg") #results = DeepFace.verify([['img1.jpg', 'img2.jpg'], ['img1.jpg', 'img3.jpg']]) print("Is verified: ", result["verified"]) ``` <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/stock-1.jpg" width="95%" height="95%"></p> Herein, face pairs could be exact image paths, numpy array or base64 encoded images. **Face recognition** - [`Demo`](https://youtu.be/Hrjp-EStM_s) Face recognition requires to apply face verification several times. Herein, deepface offers an out-of-the-box find function to handle this action. It stores the representations of your facial database and you don't have to find it again and again. In this way, you can apply [face recognition](https://sefiks.com/2020/05/25/large-scale-face-recognition-for-deep-learning/) data set as well. The find function returns pandas data frame if a single image path is passed, and it returns list of pandas data frames if list of image paths are passed. ```python from deepface import DeepFace import pandas as pd df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db") #dfs = DeepFace.find(img_path = ["img1.jpg", "img2.jpg"], db_path = "C:/workspace/my_db") ``` <p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/icon/stock-6-v2.jpg" width="95%" height="95%"></p> Herein, image path argument could be exact image path, numpy array or base64 encoded image. Also, you are expected to store your facial image data base in the folder that you passed to the db_path argument with .jpg or .png extension. **Large Scale Face Recognition** - [`Demo with Elasticsearch`](https://youtu.be/i4GvuOmzKzo), [`Demo with Spotify Annoy`](https://youtu.be/Jpxm914o2xk) You can store facial embeddings in nosql databases. In this way, you can have the power of the map reduce technology. Here, you can find some implementation experiments with [mongoDb](https://sefiks.com/2021/01/22/deep-face-recognition-with-mongodb/), [Cassandra](https://sefiks.com/2021/01/24/deep-face-recognition-with-cassandra/) and [Hadoop](https://sefiks.com/2021/01/31/deep-face-recognition-with-hadoop-and-spark/). Notice that face recognition has O(n) time complexity and this would be problematic for millions level data and limited hardware. Herein, approximate nearest neighbor (a-nn) algorithm reduces the time complexity dramatically. [Spotify Annoy](https://sefiks.com/2020/09/16/large-scale-face-recognition-with-spotify-annoy/), [Facebook Faiss](https://sefiks.com/2020/09/17/large-scale-face-recognition-with-facebook-faiss/) and [NMSLIB](https://sefiks.com/2020/09/19/large-scale-face-recognition-with-nmslib/) are amazing a-nn libraries. Besides, [Elasticsearch](https://sefiks.com/2020/11/27/large-scale-face-recognition-with-elasticsearch/) wraps an a-nn algorithm and it offers highly scalability feature. You should run deepface within those a-nn frameworks if you have really large scale data sets. **Face recognition models** - [`Demo`](https://youtu.be/i_MOwvhbLdI) Deepface is a **hybrid** face recognition package. It currently wraps the **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/) and [`Dlib`](https://sefiks.com/2020/07/11/face-recognition-with-dlib-in-python/). The default configuration verifies faces with VGG-Face model. You can set the base model while verification as illustared below. ```python models = ["VGG-Face", "Facenet", "OpenFace", "DeepFace", "DeepID", "ArcFace", "Dlib"] for model in models: result = DeepFace.verify("img1.jpg", "img2.jpg", model_name = model) df = DeepFace.find(img_path = "img1.jpg", db_path = "C:/workspace/my_db", model_name = model) ``` FaceNet, VGG-Face, ArcFace and Dlib [overperforms](https://youtu.be/i_MOwvhbLdI) than OpenFace, DeepFace and DeepID based on experiments. Supportively, FaceNet got 99.65%; ArcFace got 99.40%; Dlib got 99.38%; VGG-Face got 98.78%; OpenFace got 93.80% accuracy scores on [LFW data set](https://sefiks.com/2020/08/27/labeled-faces-in-the-wild-for-face-recognition/) whereas human beings could have just 97.53%. **Similarity** Face recognition models are regular [convolutional neural networks](https://sefiks.com/2018/03/23/convolutional-autoencoder-clustering-images-with-neural-networks/) and they are responsible to represent faces as vectors. Decision of verification is based on the distance between vectors. We can classify pairs if its distance is less than a [threshold](https://sefiks.com/2020/05/22/fine-tuning-the-threshold-in-face-recognition/). Distance