Using image super resolution models with vapoursynth and speeding them up with TensorRT

Last update: Aug 23, 2022

Overview

vs-RealEsrganAnime-tensorrt-docker

Using image super resolution models with vapoursynth and speeding them up with TensorRT. Also a docker image since TensorRT is hard to install. Testing showed ~70% more speed on my 1070ti compared to normal PyTorch in 480p. Using the 2x model with TensorRT and 848x480 input was 0.517x realtime speed for 24fps video.

I was forced to use onnx/onnx-tensorrt instead of NVIDIA/Torch-TensorRT because of convertion errors with PyTorch, but the only disadvantage should be that a new onnx model needs to be created for a different input resolution, which takes a bit time.

This repo uses a lot of code from HolyWu/vs-realesrgan and xinntao/Real-ESRGAN. The models are from here.

Usage:

# install docker, command for arch
yay -S docker nvidia-docker nvidia-container-toolkit
# Put the dockerfile in a directory and run that inside that directory
docker build -t realsr_tensorrt:latest .
# run with a mounted folder
docker run --privileged --gpus all -it --rm -v /home/Desktop/tensorrt:/workspace/tensorrt realsr_tensorrt:latest
# you can use it in various ways, ffmpeg example
vspipe --y4m inference.py - | ffmpeg -i pipe: example.mkv

If docker does not want to start, try this before you use docker:

# fixing docker errors
systemctl start docker
sudo chmod 666 /var/run/docker.sock

If you don't want to use docker, vapoursynth install commands are here and a TensorRT example is here.

Set the input video path in inference.py and access videos with the mounted folder. You can also choose between the 4x and 2x model.

It is also possible to directly pipe the video into mpv. Change the mounted folder path to your own videofolder and use the mpv dockerfile instead. Only tested in Manjaro.

yay -S pulseaudio

# i am not sure if it is needed, but go into pulseaudio settings and check "make pulseaudio network audio devices discoverable in the local network" and reboot

# start docker
docker run --rm -i -t \
    --network host \
    -e DISPLAY \
    -v /home/Schreibtisch/test/:/home/mpv/media \
    --ipc=host \
    --privileged \
    --gpus all \
    -e PULSE_COOKIE=/run/pulse/cookie \
    -v ~/.config/pulse/cookie:/run/pulse/cookie \
    -e PULSE_SERVER=unix:${XDG_RUNTIME_DIR}/pulse/native \
    -v ${XDG_RUNTIME_DIR}/pulse/native:${XDG_RUNTIME_DIR}/pulse/native \
    realsr_tensorrt:latest
    
# run mpv
vspipe --y4m inference.py - | mpv -

Using image super resolution models with vapoursynth and speeding them up with TensorRT

Related tags

Overview

vs-RealEsrganAnime-tensorrt-docker

Owner

Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).

Spatial-Location-Constraint-Prototype-Loss-for-Open-Set-Recognition

code for `Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation`

Codes for NAACL 2021 Paper "Unsupervised Multi-hop Question Answering by Question Generation"

Learn about Spice.ai with in-depth samples

Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language (NeurIPS 2021)

a grammar based feedback fuzzer

[NeurIPS 2020] Official repository for the project "Listening to Sound of Silence for Speech Denoising"

This project generates news headlines using a Long Short-Term Memory (LSTM) neural network.

Leaderboard and Visualization for RLCard

Machine Learning Framework for Operating Systems - Brings ML to Linux kernel

code for "Feature Importance-aware Transferable Adversarial Attacks"

A hand tracking demo made with mediapipe where you can control lights with pinching your fingers and moving your hand up/down.

In this project, we create and implement a deep learning library from scratch.

An image classification app boilerplate to serve your deep learning models asap!

Codes and Data Processing Files for our paper.

The Official Implementation of Neural View Synthesis and Matching for Semi-Supervised Few-Shot Learning of 3D Pose [NIPS 2021].

Boston House Prediction Valuation Tool

[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.