facenet | Face recognition using Tensorflow | Computer Vision library

 by   davidsandberg Python Version: Current License: MIT

kandi X-RAY | facenet Summary

kandi X-RAY | facenet Summary

facenet is a Python library typically used in Institutions, Learning, Education, Artificial Intelligence, Computer Vision, Tensorflow, OpenCV applications. facenet has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can download it from GitHub.

Face recognition using Tensorflow

            kandi-support Support

              facenet has a medium active ecosystem.
              It has 13092 star(s) with 4802 fork(s). There are 566 watchers for this library.
              It had no major release in the last 6 months.
              There are 495 open issues and 618 have been closed. On average issues are closed in 237 days. There are 45 open pull requests and 0 closed requests.
              It has a neutral sentiment in the developer community.
              The latest version of facenet is current.

            kandi-Quality Quality

              facenet has 0 bugs and 0 code smells.

            kandi-Security Security

              facenet has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.
              facenet code analysis shows 0 unresolved vulnerabilities.
              There are 0 security hotspots that need review.

            kandi-License License

              facenet is licensed under the MIT License. This license is Permissive.
              Permissive licenses have the least restrictions, and you can use them in most projects.

            kandi-Reuse Reuse

              facenet releases are not available. You will need to build from source code and install.
              Build file is available. You can build the component from source.
              facenet saves you 3130 person hours of effort in developing the same functionality from scratch.
              It has 6737 lines of code, 312 functions and 73 files.
              It has high code complexity. Code complexity directly impacts maintainability of the code.

            Top functions reviewed by kandi - BETA

            kandi has reviewed facenet and discovered the below as its top functions. This is intended to give you an instant insight into facenet implemented functionality, and help decide if they suit your requirements.
            • Bulk detect face detection
            • Create bounding box
            • Generate the bounding box for the given image
            • Calculate the NMS of boxes
            • Train the model
            • Get learning rate from file
            • Given a set of nrof images return a list of triplets
            • Adds summaries for each loss
            • Parse command line arguments
            • Parse command line arguments
            • Load and aligns input images
            • Detects the surface of the image
            • Validate training set
            • Create input pipeline
            • Given a list of nrof images return a list of triplets
            • Align a list of image data points
            • Convolutional convolution layer
            • Freeze a graph definition
            • Compute face encodings
            • Stores the revision info
            • Return the model s meta files
            • Splits the given dataset into nrof images
            • Align an image
            • Detects the face of the input image
            • Evaluate LFW training
            • Performs inception
            • Load a VGG model
            • Generate inference for images
            Get all kandi verified functions for this library.

            facenet Key Features

            No Key Features are available at this moment for facenet.

            facenet Examples and Code Snippets

            Pythondot img1Lines of Code : 12dot img1License : Permissive (MIT)
            copy iconCopy
            from keras_facenet import FaceNet
            embedder = FaceNet()
            # Gets a detection dict for each face
            # in an image. Each one has the bounding box and
            # face landmarks (from mtcnn.MTCNN) along with
            # the embedding from FaceNet.
            detections = embedder.extract(  
            Pythondot img2Lines of Code : 12dot img2no licencesLicense : No License
            copy iconCopy
            sudo apt-get install zenity
            cd facenet-darknet-inference
            #edit makefile
            mkdir data
            cd data
            touch name
            cd ..
            mkdir model  
            Jupyter Notebookdot img3Lines of Code : 11dot img3License : Permissive (MIT)
            copy iconCopy
            author="Mougeot, Guillaume and Li, Dewei and Jia, Shuai",
            editor="Nayak, Abhaya C. and Sharma, Alok",
            title="A Deep Learning Approach for Dog Face Verification and Recognition",
            booktitle="PRICAI 2019: Tre  

            Community Discussions


            Sorting a tensor list in ascending order
            Asked 2021-Dec-05 at 21:29

            I am working on a facial comparison app that will give me the closest n number of faces to my target face.

            I have done this with dlib/face_recognition as it uses numpy arrays, however i am now trying to do the same thing with facenet/pytorch and running into an issue because it uses tensors.

            I have created a database of embeddings and I am giving the function one picture to compare to them. What i would like is for it to sort the list from lowest distances to highest, and give me the lowest 5 results or so.

            here is the code I am working on that is doing the comparison. at this point i am feeding it a photo and asking it to compare against the embedding database.



            Answered 2021-Dec-05 at 16:43

            Unfortunately I cannot test your code, but to me it seems like you are operation on a python list of tuples. You can sort that by using a key:

            Source https://stackoverflow.com/questions/70232894


            Can't open "face_detector\deploy.prototxt" in function 'cv::dnn::ReadProtoFromTextFile'
            Asked 2021-Nov-26 at 17:44

            I'm trying to learn python, for detect someone used mask or not.

            when i run this code



            Answered 2021-Nov-26 at 17:44

             You have to make sure that files deploy.prototxt and res10_300x300_ssd_iter_140000.caffemodel are in the correct directory, then use os.path.join

            Source https://stackoverflow.com/questions/70118899


            PermissionError: [Errno 13] Permission denied: .deepface
            Asked 2021-Oct-22 at 10:59

            I have installed a basic python server with deepface library with apache2 on ubuntu.

            The library makes a .deepface directory on app initialization but it is unable to do so due to permission denied error as it's hidden in linux by default. I am getting the following error



            Answered 2021-Oct-22 at 10:59

            You can give permission to that hidden folder by typing sudo chmod 777 -R /var/www/.deepface. Make sure cheking the permission by cd /var/www/ and ls -lth

            Source https://stackoverflow.com/questions/69675561


            How to set up a environment for python application development in Docker Desktop
            Asked 2021-Aug-14 at 10:37

            I am following this guide to build an environment to develop an facial recognition project in.
            I've pulled the image provided in the guide as shown here using the command docker pull colemurray/medium-facenet-tutorial in the Desktop Docker.
            I am running a container with the image but I do not understand how I can develop an application in it (e.g having access to the modules downloaded in Docker)
            The only action I think I can take here is opening the CLI of the container as shown here but I can't find any guide to use it to add the local folder into the environment.

            I understand that using anaconda, I'll just have to activate a environment and run jupyter notebook to develop in that environment and I am trying to do the exact same thing with Docker, but I fail make the same connection, any advice will be greatly appreciated.



            Answered 2021-Aug-14 at 10:37

            You have three options here:

            1. Keep the Dockerfile in your workdirectory and adding a copy command in Dockerfile that will copy your python files inside docker container. So at the build time your container is built with with the files in it.

            Source https://stackoverflow.com/questions/68782289


            Can DeepFace verify() accept an image array or PIL Image object?
            Asked 2021-Jun-08 at 12:03

            My DeepFace Implementation



            Answered 2021-Jun-06 at 10:43

            If you are using this module, the documentation says:

            Herein, face pairs could be exact image paths, numpy array or base64 encoded images

            So, presumably, you can make your PIL Images into Numpy arrays like this:

            Source https://stackoverflow.com/questions/67856738


            How to store FaceNet data efficiently?
            Asked 2021-May-15 at 23:18

            I am using the Facenet algorithm for face recognition. I want to create application based on this, but the problem is the Facenet algorithm returns an array of length 128, which is the face embedding per person.

            For person identification, I have to find the Euclidian difference between two persons face embedding, then check that if it is greater than a threshold or not. If it is then the persons are same; if it is less then persons are different.

            Let's say If I have to find person x in the database of 10k persons. I have to calculate the difference with each and every person's embeddings, which is not efficient.

            Is there any way to store this face embedding efficiently and search for the person with better efficiency?

            I guess reading this blog will help the others.

            It's in detail and also covers most aspects of implementation.

            Face recognition on 330 million faces at 400 images per second



            Answered 2021-May-11 at 05:20

            Sounds like you want a nearest neighbour search. You could have a look at the various space partitioning data structures like kd-trees

            Source https://stackoverflow.com/questions/67462421


            Show Mask Object Detection On Screen instead of Camera
            Asked 2021-Apr-22 at 10:09

            So I've been following this tutorial to detect if person wearing mask or not on camera and got everything to work when using the camera by using the following code:



            Answered 2021-Apr-22 at 10:09

            the problem is from reading your data from MSS. MSS returns raw pixels in the BGRA form (Blue, Green, Red, Alpha).you can read about it from here. you can convert into BGR via cvtColor:

            Source https://stackoverflow.com/questions/67204560


            TypeError: Cannot create initializer for non-floating point type . When running "train_tripletloss.py"
            Asked 2021-Apr-07 at 03:19

            I am new at tensorflow and models training. I am using the face recognition algorithm based on yolo and facenet. i am now trying to train my own model. But i get an error everytime I do so. I would be very grateful to you if you help me solve it. Thank you in advance. here is the link to the code : https://github.com/AzureWoods/faceRecognition-yolo-facenet/blob/master/train_tripletloss.py

            here is t the error:



            Answered 2021-Apr-07 at 03:19

            Try add image = tf.to_float(image) in train_tripleloss.py where the below screenshot indicates.

            Source https://stackoverflow.com/questions/66737908


            Cannot set headers after they are sent to client
            Asked 2021-Mar-22 at 09:38

            I am creating an api that will call a python script using python-shell in nodejs.However when I am running the api,the api returns the error of "Cannot set headers after they have been sent to the client".Below is the code for the api.



            Answered 2021-Mar-22 at 06:29

            If this if loop get executed a response will be send

            Source https://stackoverflow.com/questions/66740844


            How do I make Input type and weight type same?
            Asked 2021-Jan-09 at 13:09

            I am getting a runtime error that says inputs and weights must be on same. However I made sure that my model and input are on the same device yet I cannot get rid of the error. As far as I read, I know that my input data is not on GPU . Since, In this case image is an input so I tried img = torch.from_numpy(img).to(device) and pred = model(img)[0].to(device but no luck. Please let me know what can be done.

            Here's the code:



            Answered 2021-Jan-09 at 13:09

            You need to send the input tensor to your device, not its result:

            Source https://stackoverflow.com/questions/65642468

            Community Discussions, Code Snippets contain sources that include Stack Exchange Network


            No vulnerabilities reported

            Install facenet

            You can download it from GitHub.
            You can use facenet like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.


            For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .
            Find more information at:

            Find, review, and download reusable Libraries, Code Snippets, Cloud APIs from over 650 million Knowledge Items

            Find more libraries
          • HTTPS


          • CLI

            gh repo clone davidsandberg/facenet

          • sshUrl


          • Stay Updated

            Subscribe to our newsletter for trending solutions and developer bootcamps

            Agree to Sign up and Terms & Conditions

            Share this Page

            share link