facenet-pytorch
facenet-pytorch copied to clipboard
timesler
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
I have small experiment to extract face from a photo. This is my config: ``` def face_detector(img): mdl = MTCNN(image_size=256, margin=0, min_face_size=20, thresholds=[0.6, 0.7, 0.7], factor=0.709, select_largest=True, selection_method="largest", post_process=True, keep_all=False,...
It happened when i run the file named "run.py" Running on device: cpu Traceback (most recent call last): File "C:\Users\HP\facenet_pytorch\CV_P4\run.py", line 22, in embed = np.load(open('embedimg.npy','rb')) File "C:\Users\HP\anaconda3\lib\site-packages\numpy\lib\npyio.py", line 444,...
Is there a way to save a embedding face to a .pkl or .npz and load it later for inference Let say after I do image embeddings with its label....
in mtcnn.py the function prewhiten is not called. I wonder then whether the returned images are in the same form the pre-trained models expect. There is function fixed_image_standardization, but it...
Hi, thanks for your remarkable work! I'm trying to reproduce some paper results and in order to do so I need a version of the FaceNet model pre-trained on MS-Celeb-1M....
Hi, I'm developing a face verification system, so I'm using mtcnn to detect faces and then do the verification step. The code I have is something like: ``` face_detect, prob...
Hello, When I use MTCNN to detect faces, I found that the detection performance with BGR input is better than RGB input? Is the MTCNN trained with BGR input? And...
I installed torch1.8.1 (in the anaconda virtual environment) under Win10, and my computer cannot connect to the Internet. I use pip to install the repository. But the default torch version...
Thanks for your great job and kind sharing. I just wonder what motivated you to design the architecture, InceptionResnetV1? Did you release any paper already? Thanks in advance.
