Open Klanly opened 4 years ago
Could you just share the bin files instead of pointing to the Colab script? Also those file paths for the drive should be not working for other users I think
Could you just share the bin files instead of pointing to the Colab script? Also those file paths for the drive should be not working for other users I think
This the converted weights& prog I currently use.. https://github.com/Klanly/lunusbuild/releases/download/gcgghq/SR.zip
1x ( cmd: realsr.exe -m c -s 1 ) is "Fatality DeBlur"; 4x ( cmd: realsr.exe -m c ) is "FatalimiX".
Weights form: https://upscale.wiki/wiki/Model_Database
default input = tibr_o.jpg default output = output.png
@Klanly How can you specify a different model? Something like realrsr.exe -m "DF2K_JPEG" (if the folder is named that way) doesn't seem to work And what does -m c do?
@Klanly How can you specify a different model? Something like realrsr.exe -m "DF2K_JPEG" (if the folder is named that way) doesn't seem to work And what does -m c do?
https://github.com/Klanly/realsr-ncnn-vulkan/blob/master/src/Readme/Readme.md 'a'=models-DF2K_JPEG, 'b'=models-DF2K, 'c'=models-ESRGAN
So, -m a = -m "DF2K_JPEG" -m b = -m "DF2K"
I made a google colab script to convert ESRGAN (old Architecture) pth files to .param and .bin:
ncnnconv.zip, rename it to .7z (to_onnx.py .etc from github.com/achie27/super-resolution )
Replace 'models-DF2K/x4.bin' with the generated x4_fp32.bin or x4_fp16.bin then that's it.
There are about +-3 value bias per channel, comparing to it's original pytorch results.