Face alignment speed up and GPU usage about face.evolve HOT 12 OPEN

@Wenlong0913 hello,I also want to improve the speed ,but there is poor promotion after using cuda. Have you find better method to accelerate?If so,can you please tell me?Thank you very much.

from face.evolve.

@Wenlong0913 hello,I also want to improve the speed ,but there is poor promotion after using cuda. Have you find better method to accelerate?If so,can you please tell me?Thank you very much.

Nope.
Perhaps you can try this implementation. It's faster.
https://github.com/Seanlinx/mtcnn

from face.evolve.

@Wenlong0913 I am facing the same problem. Could you give some hints on how much it is faster than this one? And do you think the key point of low gpu usage is mtcnn itself or in-efficient implementation? Also, in your provided mtcnn, there is no prediction of landmarks. How do you utilize it to align face?

from face.evolve.

Check out this fork: https://github.com/innerlee/face.evoLVe.PyTorch

Speed Comparison

original

In [1]: from PIL import Image 
   ...: from detector import detect_faces                                                                

In [2]: img = Image.open('../disp/Fig1.png').convert('RGB')                                                             

In [3]: %time detect_faces(img)                                                                                         
CPU times: user 2.85 s, sys: 172 ms, total: 3.02 s
Wall time: 610 ms

the fork

In [1]: from PIL import Image                                                                                           

In [2]: from evolveface import detect_faces, show_results                                                               

In [3]: img = Image.open('disp/Fig1.png').convert('RGB')

In [4]: %time detect_faces(img)                                                                                         
CPU times: user 255 ms, sys: 6.05 ms, total: 261 ms
Wall time: 42.3 ms

from face.evolve.

@innerlee so it's all about pillow-simd?

from face.evolve.

There are lots of code optimization also

from face.evolve.

@innerlee Does it affect model performance?

from face.evolve.

Purely speed changes. The bottleneck is not model inference.

from face.evolve.

@innerlee I'm checking it out. Great work

from face.evolve.

@innerlee Hello, can u share what's the estimated time for training this repo using full dataset of Celeb-1M? I tried using 4 GPU but my estimated time is too long like 200 days for a single batch. I cannot believe it. After ten hours of training using only 1/3 of data, it's still at the first epoch with batch 1920/411750. Can u share ur training status? Thx

from face.evolve.

I use the provided weights for inference. Haven't tried training 🤷

from face.evolve.

I also have this issue, I'm running the dataset on Tesla K80

from face.evolve.