I want to build a face recognizer using the pretrained models given in the repository.

Hi <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url="

hi, <a class="user-mention notranslate" data-hovercard-type="user" data-hovercard-url=

Use pretrained ResNet50 model for Face Recognition on my own dataset about arcface-tf2 HOT 3 CLOSED

peteryux commented on May 23, 2024

Use pretrained ResNet50 model for Face Recognition on my own dataset

from arcface-tf2.

peteryuX commented on May 23, 2024

Hi @iamrishab , nice to hear from you~
I briefly explain what I know, and hope that can help you.

The calculating of the embedding vector should like bellow (I thinks the code part you proved didn't have obvious mistake)
Crop RGB format [0~255] face image with alignment method -> re-scale to [0~1] -> feed into pre-train model -> normalize output embedding vector
In the LFW dataset use threshold 1.32 to distinguish identity by l2-norm distance between embedding vectors.

from arcface-tf2.

iamrishab commented on May 23, 2024

Hi @peteryuX thank you for your response.
I will surely try this out and revert in case of any further queries.

from arcface-tf2.

lixianwa commented on May 23, 2024

hi, @iamrishab I have some problem，how did you solve it ?

from arcface-tf2.