DPIR function for VapourSynth
Project description
DPIR
Plug-and-Play Image Restoration with Deep Denoiser Prior, based on https://github.com/cszn/DPIR.
Dependencies
- ncnn. Note that the official Python package is not built with Vulkan compute support. Windows users can install the wheel from https://github.com/HolyWu/ncnn/releases/latest. Non-windows users have to build from source using my fork (requires Vulkan SDK):
git clone https://github.com/HolyWu/ncnn.git --depth 1
cd ncnn
git submodule update --init --recursive --depth 1
pip install .
- VapourSynth R55 or later.
Installation
pip install -U vsdpir_ncnn
python -m vsdpir_ncnn
Usage
from vsdpir_ncnn import DPIR
dpir = DPIR(task='deblock')
ret = dpir.run(clip, strength=25)
See __init__.py
for the description of the parameters.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
File details
Details for the file vsdpir_ncnn-2.0.0-py3-none-any.whl
.
File metadata
- Download URL: vsdpir_ncnn-2.0.0-py3-none-any.whl
- Upload date:
- Size: 14.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.10.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | e12e69a3249101ebf541d9abc83971d2d956a8fdec4433a5750490164184a3e8 |
|
MD5 | 71c6d4f31bd0c4214e755576d46e2192 |
|
BLAKE2b-256 | 96bbadcde47890e94a7143aaab715cd072980a413bb6bfb0fef2fd00b098a6c3 |