Benchmarks

From Upscale Wiki
Jump to navigation Jump to search

BasicSR (Training)

GPU (or CPU) OS CUDA Version cudnn Version Driver Version Pytorch Version BasicSR Version Scale model architecture Tile size Batch size OTF Time per 1000 iterations
GTX 1080 TI 11Gb (Asus OC version) Arch Linux 10.1.168-4 7.6.1.34-1 430.40-2 1.1.0-8 Victorc's Fork #754b476 4x PPON (Phase 1) 192 18 yes 3648.178s (01h, 00min, 48s, 178ms)
Google Colaboratory, GPU Runtime Ubuntu 10.0.130-10 ? ? 1.1.0 ? 1x 128 2 no 2721.390 (00h, 45min, 21s, 390ms)

ESRGAN

GPU (or CPU) OS CUDA Version cudnn Version Driver Version Pytorch Version ESRGAN Version Scale Image dimensions Time needed for image
sample sample sample sample sample sample sample 4x sample 0.0s (00h, 00min, 00s, 000ms)
CPU (example-manufacturer Model) sample sample - - sample sample 4x sample 0.0s (00h, 00min, 00s, 000ms)