search

google-research / maxim

[CVPR 2022 Oral] Official repository for "MAXIM: Multi-Axis MLP for Image Processing". SOTA for denoising, deblurring, deraining, dehazing, and enhancement.
https://arxiv.org/abs/2201.02973
Apache License 2.0
1.02k stars 110 forks source link

About runtimes of the models #38

Open barisbatuhan opened 1 year ago

barisbatuhan commented 1 year ago

Do you have any runtime information on individual model versions on specific image dimensions? I am using 720p images, and the iteration takes > 20 seconds per image on an A6000 GPU. I get no errors on the execution, and the GPU memory is allocated. I am confident that the model runs on GPU. I use CUDA 11.3 with CuDNN 8.2.

barisbatuhan commented 1 year ago

The model I run is the Image Enhancement Model - FiveK