-
I run the LFW database and the best threshold for accuracy is 1.24, and the accuracy is 99.2%
But when I run my own Asian people database, the best threshold is 0.76, and the accuracy is 94.2%
I am …
-
First, thank you for your contribution.
I follow your step, used CASIA data and 'mnist_siamese_solver.prototxt', 'CASIA_train_test.prototxt' in 'caffe_proto' folder training CNN without mean file by …
-
I tried to finetune at L-2 layer :
ftune_vlist = [v for v in all_vars if not v.name.startswith('Mixed_8b')] in inception-resnet-v1,
and train on my_classifier.py to get .pkl file,
but I got the e…
-
Hi~
Thank you for your great work.
Does the reported accuracy result on validation data (e.g. LFW, MegaFace) apply face alignment process (e.g., MTCNN)?
Thank you.
-
ghost updated
5 years ago
-
hi,
seems so great,but how to begin for a newer ?
any advice or suggestion will be appreciated.
Thx
-
I downloaded Real-world masked face recognition dataset from https://drive.google.com/open?id=1UlOk6EtiaXTHylRUx2mySgvJX9ycoeBp.
However, I can't find the annotation labels of the face dataset. So I…
-
Hello,
I am training a mobilefacenet(embedding=128) with CASIA_Webface using arcface_torch. The loss has decreased from 53.7805 to 2.8381. However, the verification accuracies of lfw, cfp_fp, and a…
-
I retrained the SpherefaceNet-20 from scratch but the performance on LFW cannt reach 99.30%.
Evaluation log is as below:
```
fold ACC
----------------
1 98.83%
2 98.83%
3 98.50%
4 99.17%
5 99…
-
I have used MTCNN to extract faces on a news video. I want to identify the face of Donald Trump. My images: https://www.dropbox.com/s/k137md6qyvu2kbf/images.zip?dl=0.
My approach:
1) Detect faces …