Difference between revisions of "Benchmarks"

From Upscale Wiki
Jump to navigation Jump to search
m (Messing with column widths)
m (Adding a scale column)
Line 3: Line 3:
 
{| class="wikitable sortable" width="100%"
 
{| class="wikitable sortable" width="100%"
 
|-
 
|-
! width="115px" | GPU (or CPU) !! width="82px" | OS !! width="82px" | CUDA Version !! width="82px" | cudnn Version !! width="82px" | Driver Version !! width="82px" | Pytorch Version !! width="70px" | BasicSR Version !! model architecture !! Tile size !! Batch size !! OTF !! Time per 1000 iterations
+
! width="115px" | GPU (or CPU) !! width="82px" | OS !! width="82px" | CUDA Version !! width="82px" | cudnn Version !! width="82px" | Driver Version !! width="82px" | Pytorch Version !! width="70px" | BasicSR Version !! width="70px" | 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 || PPON (Phase 1) || 192 || 18 || yes || 3648.178s (01h, 00min, 48s, 178ms)
+
| 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)
 
|}</div>
 
|}</div>
  
Line 12: Line 12:
 
{| class="wikitable sortable" width="100%"
 
{| class="wikitable sortable" width="100%"
 
|-
 
|-
! width="115px" | GPU (or CPU) !! width="82px" | OS !! width="82px" | CUDA Version !! width="82px" | cudnn Version !! width="82px" | Driver Version !! width="82px" | Pytorch Version !! width="70px" | ESRGAN Version !! Image dimensions !! Time needed for image
+
! width="115px" | GPU (or CPU) !! width="82px" | OS !! width="82px" | CUDA Version !! width="82px" | cudnn Version !! width="82px" | Driver Version !! width="82px" | Pytorch Version !! width="70px" | ESRGAN Version !! width="70px" | Scale !! Image dimensions !! Time needed for image
 
|-
 
|-
| sample || sample|| sample || sample || sample || sample || sample || sample || 0.0s (00h, 00min, 00s, 000ms)
+
| sample || sample|| sample || sample || sample || sample || sample || 4x || sample || 0.0s (00h, 00min, 00s, 000ms)
 
|-
 
|-
| CPU (example-manufacturer Model) || sample || sample || - || - || sample || sample || sample || 0.0s (00h, 00min, 00s, 000ms)
+
| CPU (example-manufacturer Model) || sample || sample || - || - || sample || sample || 4x || sample || 0.0s (00h, 00min, 00s, 000ms)
 
|}
 
|}
 
</div>
 
</div>

Revision as of 22:34, 13 August 2019

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)

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)