011-grace-loss-resilient-real-time-video-through-neural-codecs

https://github.com/szu-advtech-2024/011-grace-loss-resilient-real-time-video-through-neural-codecs

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
○
.zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (8.5%) to scientific vocabulary

Last synced: 10 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: SZU-AdvTech-2024
Default Branch: main
Size: 0 Bytes

Statistics

Stars: 0
Watchers: 0
Forks: 0
Open Issues: 0
Releases: 0

Created over 1 year ago · Last pushed over 1 year ago

Metadata Files

Citation

https://github.com/SZU-AdvTech-2024/011-GRACE-Loss-Resilient-Real-Time-Video-through-Neural-Codecs/blob/main/

# GRACE: Loss-Resilient Real-Time Video through Neural Codecs

## Important License Information 

Before using any software or code from this repository, please refer to the LICENSE file for detailed terms and conditions. It is crucial to understand that while the majority of the code in this repository is governed by the Academic Software License  2023 UChicago

Additionally, please note that the content within the following specific subfolders and files ("baselines/error_concealment", "grace/subnet", and "grace/net.py") did not originate from the authors and may be subject to different terms and conditions, not covered under the provided license. 

## 

```bash
sudo apt install ffmpeg ninja-build # install the ffmpeg and ninja
conda env create -f env.yml # creating the conda environment
```

## 

: https://drive.google.com/file/d/1iQhTfb7Kew_z97kDVoj2vOmQqaNjBK9J/view?usp=sharing

: https://drive.google.com/file/d/1IWD-VUc0RPXXhBzoH5j9YD6bl8kzYYJ1/view?usp=sharing

```bash
cp /your/download/path/grace_models.tar
cd models/
tar xzvf grace_models.tar 

cd ../videos/
cp /your/download/path/GraceVideos.zip .
unzip GraceVideos.zip
```

## 

```bash
# activate the conda env
conda activate grace-test

# run Grace
LD_LIBRARY_PATH=libs/:${LD_LIBRARY_PATH} python3 grace-gpu.py

# run pretrained AE models
LD_LIBRARY_PATH=libs/:${LD_LIBRARY_PATH} python3 pretrained-gpu.py

# run h265/h264 baseline
# NOTE: after running this, you may have to restart your terminal
LD_LIBRARY_PATH=libs/:${LD_LIBRARY_PATH} python3 h26x.py

# run error concealment
# WARNING: this could take a long time (couple of hours)
LD_LIBRARY_PATH=libs/:${LD_LIBRARY_PATH} python3 error-concealment.py
```

## 

```bash
cd results/
python3 plot.py
```

Owner

Name: SZU-AdvTech-2024
Login: SZU-AdvTech-2024
Kind: organization

Repositories: 1
Profile: https://github.com/SZU-AdvTech-2024

Citation (citation.txt)

@inproceedings{REPO011,
    author = "Cheng, Yihua and Zhang, Ziyi and Li, Hanchen and Arapin, Anton and Zhang, Yue and Zhang, Qizheng and Liu, Yuhan and Du, Kuntai and Zhang, Xu and Yan, Francis Y. and Mazumdar, Amrita and Feamster, Nick and Jiang, Junchen",
    booktitle = "21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)",
    month = "April",
    pages = "509--531",
    publisher = "USENIX Association",
    title = "{{GRACE}: {Loss-Resilient} {Real-Time} Video through Neural Codecs}",
    year = "2024"
}

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science