thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

Update VGG7 example README to include model download instructions

Browse source
This commit is contained in:
20kdc 2021-05-30 19:23:19 +01:00
parent 865fd4b5cd
commit 55a02c0c7f
1 changed files with 7 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

9
examples/neural_network_vgg7/README.md
View file

@ -2,9 +2,14 @@
This demonstrates performing image upscaling using Python and vulkan-kompute.
To import an existing VGG7 model (assuming you have https://github.com/nagadomi/waifu2x/ cloned somewhere):
To import the no-noise-compensation VGG7 model (into `model-kipper`):
`python3 import_vgg7.py waifu2x/models/vgg_7/art/scale2.0x_model.json`
```
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):