FPS of the model and small face about retinaface_pytorch HOT 4 CLOSED

And small face is difficult to detect, such as 0_Parade_marchingband_1_188 and 0_Parade_marchingband_1_465.

from retinaface_pytorch.

And small face is difficult to detect, such as 0_Parade_marchingband_1_188 and 0_Parade_marchingband_1_465.

Speed has not been tested yet.Maybe in the future.
And for small faces, you can change size of input from default 640 to a larger scale.
Simply change detect.py, line 77:
resized_img = resize(padded_img.float(),(640,640))

from retinaface_pytorch.

Thanks for your work!
Is there any speed test(FPS) of your model? thx!

hi,
you will see speed test in my github, i have converted the model to caffe and then to tensorrt int8 model, you can test it!
https://github.com/clancylian/retinaface

from retinaface_pytorch.

Thx, I tested the FPS, almost 26 FPS in widerface val for (640,640).

from retinaface_pytorch.