ageitgey / face_recognition_models

Trained models for the face_recognition python library

Face Recognition Models

This package contains only the models used by face_recognition.

See face_recognition for more information.

These models were created by Davis King and are licensed in the public domain or under CC0 1.0 Universal. See LICENSE.

face_recognition_models's Issues

module 'face_recognition_models' has no attribute 'face_locations'

when i am running the below line of code :
face_recognition_models.face_locations(rgb,model="cnn")
I am getting this error:
module 'face_recognition_models' has no attribute 'face_locations'

face_recognition_models contains same functions of face_recognition but why i am getting this error.

Bad CRC-32 for shape_predictor_68_face_landmarks.dat

• face_recognition version: 1.3.0
• Python version: 3.7.3
• Operating System: Raspbian GNU/Linux 10 (buster)

Description

Trying to install face_recognition via pip.

What I Did

sudo pip3 install face_recognition

Result:
zipfile.BadZipFile: Bad CRC-32 for file 'face_recognition_models/models/shape_predictor_68_face_landmarks.dat'

Full output of pip3 in attached file:
pip face_recognition.txt

Methods available in face_recognition_models

What are the various methods available for coding in face_recognition_models?For loading an image file and etc.

Slow feedforward computing time for dlib_face_recognition_resnet_model_v1?

dlib_face_recognition_resnet_model_v1 model compute_feature_descriptor method is taking 0.35 sec for a single image?
Is it normal time?

Face recognition model

• face_recognition version:
• Python version:
• Operating System:

Description

I am unable to install face_recognition_model.
If anybody knows please help me .

When running on a CPU-only Google Colab kernel, no CUDA-capable device is detected

• face_recognition version: 0.3
• Python version: 3.6
• Operating System: Google Colab (cpu-only)

Description

My face encoder doesn't work when running on a CPU-only instance of Google Colab because dlib seems to expect a GPU.

What I Did

import face_recognition_models
import dlib

predictor_5_point_model = face_recognition_models.pose_predictor_five_point_model_location()
pose_predictor_5_point = dlib.shape_predictor(predictor_5_point_model)

predictor_68_point_model = face_recognition_models.pose_predictor_model_location()
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)

face_recognition_model = face_recognition_models.face_recognition_model_location()

face_encoder = dlib.face_recognition_model_v1(face_recognition_model)

And got the following error:

---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-4-2d57e5cbaae3> in <module>()
----> 1 face_encoder = dlib.face_recognition_model_v1(face_recognition_model)

RuntimeError: Error while calling cudaGetDevice(&the_device_id) in file /tmp/pip-wheel-b9ck8go0/dlib/dlib/cuda/gpu_data.cpp:201. code: 100, reason: no CUDA-capable device is detected
---------------------------------------------------------------------------

Note that this works fine on a GPU instance on Google Colab but not on a cpu-only one. And sometimes, I can't get a GPU instance on Colab which makes it impossible to run some code the uses the face_encoder (which should still work at a reasonable speed on the CPU.)

Here's a link to my Google Colab notebook to reproduce this: https://colab.research.google.com/drive/1wdCrks6Mdx-O9A77umQKUb8wCk8i43Uu

Network

What is the neural network of face detection model? Can you please tell me the architecture of the face detection model?

Cannot import Facerecognition on Pycharm

• face_recognition version: 1.3.0
• Python version: 3.10
• Operating System: Windows 11

Description

I'm trying to import Face recognition on Pycharm , and i get this error :
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
RuntimeError: Unable to open C:\Users...\venv\lib\site-packages\face_recognition_models\models\shape_predictor_68_face_landmarks.dat

i checked , the shape predictor file exists in the models folder

"C:\Users\SIMO1\OneDrive - Université Mohammed VI Polytechnique\Desktop\MVP AE\venv\Scripts\python.exe" "C:\Users\SIMO1\OneDrive - Université Mohammed VI Polytechnique\Desktop\MVP AE\Encodeur.py"
Traceback (most recent call last):
File "C:\Users\SIMO1\OneDrive - Université Mohammed VI Polytechnique\Desktop\MVP AE\Encodeur.py", line 3, in
import face_recognition
File "C:\Users\SIMO1\OneDrive - Université Mohammed VI Polytechnique\Desktop\MVP AE\venv\lib\site-packages\face_recognition_init_.py", line 7, in
from .api import load_image_file, face_locations, batch_face_locations, face_landmarks, face_encodings, compare_faces, face_distance
File "C:\Users\SIMO1\OneDrive - Université Mohammed VI Polytechnique\Desktop\MVP AE\venv\lib\site-packages\face_recognition\api.py", line 20, in
pose_predictor_68_point = dlib.shape_predictor(predictor_68_point_model)
RuntimeError: Unable to open C:\Users\SIMO1\OneDrive - Université Mohammed VI Polytechnique\Desktop\MVP AE\venv\lib\site-packages\face_recognition_models\models\shape_predictor_68_face_landmarks.dat

Process finished with exit code 1

shape_predictor_68_face_landmarks.dat.bz2 is not CC0 licensed

https://github.com/davisking/dlib-models#shape_predictor_68_face_landmarksdatbz2 says it excludes commercial use, so it cannot be CC0

Regarding Dataset On which FR models created

Please can you give Dataset on Which these FR models created ?

How to train the models on our datasets

I want to train the models on our dataset