Information about fork: This fork adds Rife4 and removes PIL. It uses numpy arrays instead.
rife-ncnn-vulkan is nihui's ncnn implementation of Real-Time Intermediate Flow Estimation for Video Frame Interpolation.
rife-ncnn-vulkan-python wraps rife-ncnn-vulkan project by SWIG to make it easier to integrate rife-ncnn-vulkan with existing python projects.
Linux/Windos/Mac X86_64 binary build releases are available now.
- However, for Linux (Like Ubuntu 18.04) with an older GLIBC (version < 2.29), you may try to use the ubuntu-1804 release or just compile it on your own.
- Windows release is not working for all python version. The version of Windows build is for python 3.9. This is a known issue: ImportError: DLL load failed while importing _rife_ncnn_vulkan_wrapper: The specified module could not be found.
For PyPI supports, we are working on it, and hope will publish it on PyPI in the future.
First, you have to install python, python development package (Python native development libs in Visual Studio), vulkan SDK and SWIG on your platform. And then, there are two ways to build it:
- Use setuptools to build and install into python package directly. (Currently in developing)
- Use CMake directly (The old way)
python setup.py installgit clone https://github.com/ArchieMeng/rife-ncnn-vulkan-python.git
cd rife-ncnn-vulkan-python
git submodule update --init --recursive
cmake -B build src
cd build
makeI used Visual Studio 2019 and msvc v142 to build this project for Windows.
Install visual studio and open the project directory, and build. Job done.
The only problem on Windows is that, you cannot use CMake for Windows GUI to generate the Visual Studio solution file and build it. This will make the lib crash on loading.
One way is using Visual Studio to open the project as directory, and build it from Visual Studio. And another way is build it from powershell just like what is written in the release.yml
RIFE (Real-Time Intermediate Flow Estimation for Video Frame Interpolation)
https://github.com/hzwer/arXiv2020-RIFE
Huang, Zhewei and Zhang, Tianyuan and Heng, Wen and Shi, Boxin and Zhou, Shuchang
https://arxiv.org/abs/2011.06294
from rife_ncnn_vulkan_python import Rife
import cv2
image0 = cv2.imread("frame1.jpg")
image1 = cv2.imread("frame3.jpg")
rife = Rife(gpuid=0, model="rife-v4", tta_mode=False, num_threads=4)
output = rife.process(image0, image1)
cv2.imwrite("output.png", output)If you encounter a crash or error, try upgrading your GPU driver:
- Intel: https://downloadcenter.intel.com/product/80939/Graphics-Drivers
- AMD: https://www.amd.com/en/support
- NVIDIA: https://www.nvidia.com/Download/index.aspx
| model | upstream version |
|---|---|
| rife | 1.2 |
| rife-HD | 1.5 |
| rife-UHD | 1.6 |
| rife-anime | 1.8 |
| rife-v2 | 2.0 |
| rife-v2.3 | 2.3 |
| rife-v2.4 | 2.4 |
| rife-v3.0 | 3.0 |
| rife-v3.1 | 3.1 |
| rife-v4 | 4 |
- https://github.com/Tencent/ncnn for fast neural network inference on ALL PLATFORMS
- https://github.com/webmproject/libwebp for encoding and decoding Webp images on ALL PLATFORMS
- https://github.com/nothings/stb for decoding and encoding image on Linux / MacOS
- https://github.com/tronkko/dirent for listing files in directory on Windows
- https://github.com/nihui/rife-ncnn-vulkan the original rife-ncnn-vulkan project