search

mks0601 / A-Convolutional-Neural-Network-Cascade-for-Face-Detection

TensorFlow implementation of "A Convolutional Neural Network Cascade for Face Detection", CVPR 2015
http://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Li_A_Convolutional_Neural_2015_CVPR_paper.pdf
109 stars 62 forks source link

why is your 12-net different of the paper? #18

Closed aloha000 closed 5 years ago

aloha000 commented 6 years ago

hi, I've noticed that your 12-net added two fully convolutional layers. Can you tell me why? Does this work better than the paper did ?

mks0601 commented 5 years ago

I cannot remember detailed things, however there is not much difference between original implementation.

aloha000 commented 5 years ago

thanks for your reply!

------------------ Original ------------------ From: Gyeongsik Moon notifications@github.com Date: Tue,Apr 23,2019 6:11 PM To: mks0601/A-Convolutional-Neural-Network-Cascade-for-Face-Detection A-Convolutional-Neural-Network-Cascade-for-Face-Detection@noreply.github.com Cc: aloha000 470333816@qq.com, Author author@noreply.github.com Subject: Re: [mks0601/A-Convolutional-Neural-Network-Cascade-for-Face-Detection] why is your 12-net different of the paper? (#18)

I cannot remember detailed things, however there is not much difference between original implementation.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.