About runtimes of the models
barisbatuhan opened this issue · comments
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.
The model I run is the Image Enhancement Model - FiveK