Hello, this is Saketh Bachu, just another deep learning enthusiast. I am a third year undergraduate student at Visvesvaraya National Institute of Technology, Nagpur. I am also a part of IvLabs ( The Robotics and AI lab of VNIT ), this is where I fell in love with AI:heart_eyes:
The topics of my interest include: Deep learning, Computer vision, Image processing, and Mathematics.
I am very keen on following research that is being done on the above mentioned fields, and the practical usage of the research excites me.
I tried to solve a couple of real-life problems with the help of my fields of interest and more information can be gathered from my repositories.
Connect with me on Linkedin and if your looking for some informal chats, here is my Instagram.
I invoke with this parameters python demo.py -m liveness.model -l le.pickle -d D:\dev\Face-Liveness-Detection -p shapepredictor
and get a problem which I can't solve.
The "shapepredictor" model you provide is dlib's 5 point landmark detection model, however you are using 68 point landmark for detecting eyes. That's why demo.py crashed with index not found error. Please change "shapepredictor" your model so that you can obtain 68 point landmark.
Also the detection of eye blink accuracy is too bad, i mean it gives random output.
You can found 68 point shape predictor model from below link. http://dlib.net/files/
PS C:\Users\M RIYAZ HUSSAIN\OneDrive\Desktop\Face-Liveness-Detection-master\Face-Liveness-Detection-master> python3.9.exe .\demo.py --model C:\work\Face-Liveness-Detection-master\liveness.model --le C:\work\Face-Liveness-Detection-master\le.pickle --detector C:\Users\MRIYAZ~1\OneDrive\Desktop\livenessnet-master\livenessnet-master\face_detector\ --shape-predictor C:\work\Face-Liveness-Detection-master
2022-03-28 15:37:20.213512: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-03-28 15:37:20.213830: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
loading face detector
loading the liveness detector
2022-03-28 15:37:22.632096: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2022-03-28 15:37:22.632654: W tensorflow/stream_executor/cuda/cuda_driver.cc:269] failed call to cuInit: UNKNOWN ERROR (303)
2022-03-28 15:37:22.638761: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: Madikera-Riyaz-Hussain
2022-03-28 15:37:22.639143: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: Madikera-Riyaz-Hussain
2022-03-28 15:37:22.639859: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
Traceback (most recent call last):
File "C:\Users\M RIYAZ HUSSAIN\OneDrive\Desktop\Face-Liveness-Detection-master\Face-Liveness-Detection-master\demo.py", line 43, in
le = pickle.loads(open(args["le"], "rb").read())
ModuleNotFoundError: No module named 'sklearn.preprocessing.label'