chenyang-zhu/yolov3-based-face-detection-tracking

This is a robot project for television live. System will tracking the host's face, making the face in the middle of the screen. Main algorithm is Yolov3, trained on WIDER FACE and tested on FDDB benchmark. Extremely fine performance!

yolov3-based-face-detection-tracking's Issues

mtcnn

你好！能不能分享一下mtcnn部分的代码，谢谢！

What is the frames per sec?

What is the frame rate for 720p or 1080p image resolution?

训练部分的代码

请问训练部分的代码您还保留着吗？希望可以提供一份参考学习

Cannot download tensorflow graph file

Hi,
I am very interested in your work on yolov3, and I wanted to test your code.
Unfortunately, I cannot download the tensoflow grah file from https://pan.baidu.com.

Would you agree to upload it to another site like dropbox or google drive, please?

Regards.

Training Process

Hello!

i used your model and it gives me amazing results. I plan to train it again on the WIDER Dataset but i wanted to ask you, how did you generate the labels from WIDER to YOLO format? do you have a small script to convert the data format?
Do you have details on your training process?

Thanks and greetz!

Can't download .pb

Hi! I can't download the .pb file, does anyone has it in Drive or smth similar?

Thanks!