thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4
llama-cpp-turboquant/examples/neural_network_vgg7
History
Alejandro Saucedo 96768a3302 UPdated examples and documentations to not require glsl deps
2021-07-21 20:30:38 +01:00
..
.gitignore Add suggested output filenames to VGG7 gitignore 2021-05-30 20:03:26 +01:00
import_vgg7.py VGG7 example 2021-05-30 18:42:35 +01:00
README.md Update VGG7 example README to include model download instructions 2021-05-30 19:23:19 +01:00
run_vgg7.py VGG7 example 2021-05-30 18:42:35 +01:00
sh_common.py VGG7 example 2021-05-30 18:42:35 +01:00
sh_conv.py UPdated examples and documentations to not require glsl deps 2021-07-21 20:30:38 +01:00
w2wbinit.png VGG7 example 2021-05-30 18:42:35 +01:00

README.md

Waifu2x VGG7 implementation

This demonstrates performing image upscaling using Python and vulkan-kompute.

To import the no-noise-compensation VGG7 model (into model-kipper):

curl -o model.json https://raw.githubusercontent.com/nagadomi/waifu2x/master/models/vgg_7/art/scale2.0x_model.json
python3 import_vgg7.py model.json

Other models from the vgg_7 set (such as https://raw.githubusercontent.com/nagadomi/waifu2x/master/models/vgg_7/photo/noise0_model.json) can be subsituted as desired.

To execute that model (no tiling is performed, so be careful about image sizes):

python3 run_vgg7.py w2wbinit.png out.png