Skip to content

anvuongb/age-estimation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

77 Commits
 
 
 
 
 
 
 
 

Repository files navigation

age-estimation

age_estimation

These codes were tested on both AMD (ROCm 2.6) and Nvidia GPU (CUDA 10)

All tensor operations come from tf and tf.keras, standalone keras was removed due to conflicts with auto_mixed_precision

Mixed precision can be enabled by setting --fp16 1. This option generally works better on Nvidia, especially Turing generation, Tesla T4 show 40% better GPU utilization when switch to fp16

GPU provider can be selected by setting --provider nvidia or --provider amd

Network tested: ResNet50, InceptionV3, InceptionResNetV2, and SEInceptionV3

face_detection

TODO

face_embedding

TODO

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages