mirror of
https://github.com/TencentARC/GFPGAN.git
synced 2026-04-23 06:10:43 +00:00
Improve inference time. #308
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @rohaantahir on GitHub (Feb 9, 2023).
Hi, I love the work. I wanted to enhance the videos of containing facial images. To do that I am converting the video to frames and processing it one by one. I wanted to know if there any solution to improve the inferrence time, so that when a big video processed it can be processed efficiently.
P.S I have RTX 3090 and core i9 high end system.
@Wong-denis commented on GitHub (Feb 17, 2023):
same issue here. For me, it took about 90ms to process an 120x160 image. I wonder if there is room for improvement.
p.s. I use RTX3060.
@rohaantahir commented on GitHub (Mar 21, 2023):
Still waiting for someone to respond and guide.
@dearkafka commented on GitHub (Mar 21, 2023):
@rohaantahir you know that 90ms is fast, right? Gfpgan is so far one of the fastest (still) given quality
@rohaantahir commented on GitHub (Mar 21, 2023):
Yeah that seems fast, but, in my system I am getting morethan 90ms could you please tell me you are using? I am using this command to execute.
python inference_gfpgan.py -i input_image -o outputPath -v 1.4 -s 2 --only_center_face --bg_upsampler none
@JGooLaaR commented on GitHub (Mar 21, 2023):
@rohaantahir , you can skip frames without faces.
@rohaantahir commented on GitHub (Mar 21, 2023):
@JGooLaaR I am doing it I am using the video that has only faces in every frame already.
@JGooLaaR commented on GitHub (Mar 21, 2023):
@rohaantahir, do you know the specific bottleneck code region?
@rohaantahir commented on GitHub (Mar 21, 2023):
I am getting this time for one image to restore of resolution 640X360.
@rohaantahir commented on GitHub (Mar 21, 2023):
no I am trying to figure it out. Could you please help me out.
@rohaantahir commented on GitHub (Mar 21, 2023):
@Wong-denis what configurations you are using can you please tell me? like which pytorch, and python version specifically you are using?
@JGooLaaR commented on GitHub (Mar 21, 2023):
@rohaantahir , you must use "Measure execution time of a function" way to find out what method is the bottleneck. Inside inference script.
@gg22mm commented on GitHub (Nov 20, 2024):