nihui / ifrnet-ncnn-vulkan

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation implemented with ncnn library

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

IFRNet ncnn Vulkan

❗ ❗ ❗ This software is in the early development stage, it may bite your cat

CI download

ncnn implementation of IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation.

ifrnet-ncnn-vulkan uses ncnn project as the universal neural network inference framework.

Download Windows/Linux/MacOS Executable for Intel/AMD/Nvidia GPU

https://github.com/nihui/ifrnet-ncnn-vulkan/releases

This package includes all the binaries and models required. It is portable, so no CUDA or PyTorch runtime environment is needed :)

About IFRNet

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation

https://github.com/ltkong218/IFRNet

Lingtong Kong, Boyuan Jiang, Donghao Luo, Wenqing Chu, Xiaoming Huang, Ying Tai, Chengjie Wang, Jie Yang

https://arxiv.org/abs/2205.14620

Usages

Input two frame images, output one interpolated frame image.

Example Commands

./ifrnet-ncnn-vulkan -0 0.jpg -1 1.jpg -o 01.jpg
./ifrnet-ncnn-vulkan -i input_frames/ -o output_frames/

Example below runs on CPU, Discrete GPU, and Integrated GPU all at the same time. Uses 2 threads for image decoding, 4 threads for one CPU worker, 4 threads for another CPU worker, 2 threads for discrete GPU, 1 thread for integrated GPU, and 4 threads for image encoding.

./ifrnet-ncnn-vulkan -i input_frames/ -o output_frames/ -g -1,-1,0,1 -j 2:4,4,2,1:4

Video Interpolation with FFmpeg

mkdir input_frames
mkdir output_frames

# find the source fps and format with ffprobe, for example 24fps, AAC
ffprobe input.mp4

# extract audio
ffmpeg -i input.mp4 -vn -acodec copy audio.m4a

# decode all frames
ffmpeg -i input.mp4 input_frames/frame_%08d.png

# interpolate 2x frame count
./ifrnet-ncnn-vulkan -i input_frames -o output_frames

# encode interpolated frames in 48fps with audio
ffmpeg -framerate 48 -i output_frames/%08d.png -i audio.m4a -c:a copy -crf 20 -c:v libx264 -pix_fmt yuv420p output.mp4

Full Usages

Usage: ifrnet-ncnn-vulkan -0 infile -1 infile1 -o outfile [options]...
       ifrnet-ncnn-vulkan -i indir -o outdir [options]...

  -h                   show this help
  -v                   verbose output
  -0 input0-path       input image0 path (jpg/png/webp)
  -1 input1-path       input image1 path (jpg/png/webp)
  -i input-path        input image directory (jpg/png/webp)
  -o output-path       output image path (jpg/png/webp) or directory
  -n num-frame         target frame count (default=N*2)
  -s time-step         time step (0~1, default=0.5)
  -m model-path        ifrnet model path (default=IFRNet_Vimeo90K)
  -g gpu-id            gpu device to use (-1=cpu, default=auto) can be 0,1,2 for multi-gpu
  -j load:proc:save    thread count for load/proc/save (default=1:2:2) can be 1:2,2,2:2 for multi-gpu
  -x                   enable tta mode
  -u                   enable UHD mode
  -f pattern-format    output image filename pattern format (%08d.jpg/png/webp, default=ext/%08d.png)
  • input0-path, input1-path and output-path accept file path
  • input-path and output-path accept file directory
  • num-frame = target frame count
  • time-step = interpolation time
  • load:proc:save = thread count for the three stages (image decoding + ifrnet interpolation + image encoding), using larger values may increase GPU usage and consume more GPU memory. You can tune this configuration with "4:4:4" for many small-size images, and "2:2:2" for large-size images. The default setting usually works fine for most situations. If you find that your GPU is hungry, try increasing thread count to achieve faster processing.
  • pattern-format = the filename pattern and format of the image to be output, png is better supported, however webp generally yields smaller file sizes, both are losslessly encoded

If you encounter a crash or error, try upgrading your GPU driver:

Build from Source

  1. Download and setup the Vulkan SDK from https://vulkan.lunarg.com/
  • For Linux distributions, you can either get the essential build requirements from package manager
dnf install vulkan-headers vulkan-loader-devel
apt-get install libvulkan-dev
pacman -S vulkan-headers vulkan-icd-loader
  1. Clone this project with all submodules
git clone https://github.com/nihui/ifrnet-ncnn-vulkan.git
cd ifrnet-ncnn-vulkan
git submodule update --init --recursive
  1. Build with CMake
  • You can pass -DUSE_STATIC_MOLTENVK=ON option to avoid linking the vulkan loader library on MacOS
mkdir build
cd build
cmake ../src
cmake --build . -j 4

TODO

  • UHD mode
  • adaptive image mean
  • test-time temporal augmentation aka TTA-t

Sample Images

Original Image

origin0 origin1

Interpolate with ifrnet IFRNet_Vimeo90K model

ifrnet-ncnn-vulkan.exe -m models/IFRNet_Vimeo90K -0 0.png -1 1.png -o out.png

ifrnet

Original IFRNet Project

Other Open-Source Code Used

About

IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation implemented with ncnn library

License:MIT License


Languages

Language:C 82.9%Language:C++ 14.0%Language:CMake 3.1%