百科.dev
全部条目在线工具AI 编程趋势榜开源项目技术资讯提交条目
登录
< 返回工具列表
E

ECBSR

> 编程语言
开源

基于边缘的卷积块,用于移动设备的实时超高分辨率,ACM Multimedia 2021

389 stars0 点赞3 次浏览
访问官网GitHub

工具介绍

基于边缘的卷积块,用于移动设备的实时超高分辨率,ACM Multimedia 2021

Codes for ECBSR

Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices
Xindong Zhang, Hui Zeng, Lei Zhang
ACM Multimedia 2021

Codes

An older version implemented based on EDSR is place on /legacy folder. For more details, please refer to /legacy/README.md. The following is the lighten version implemented by us.

Dependencies & Installation

Please refer to the following simple steps for installation.

bash
git clone https://github.com/xindongzhang/ECBSR.git
cd ECBSR
pip install -r requirements.txt

Training and benchmarking data can be downloaded from DIV2K and benchmark, respectively. Thanks for excellent work by EDSR.

Training & Testing

You could also try less/larger batch-size, if there are limited/enough hardware resources in your GPU-server. ECBSR is trained and tested with colors=1, e.g Y channel out of Ycbcr.

bash
cd ECBSR

## ecbsr-m4c8-x2-prelu(you can revise the parameters of the yaml-config file accordding to your environments)
python train.py --config ./configs/ecbsr_x2_m4c8_prelu.yml

## ecbsr-m4c8-x4-prelu
python train.py --config ./configs/ecbsr_x4_m4c8_prelu.yml

## ecbsr-m4c16-x2-prelu
python train.py --config ./configs/ecbsr_x2_m4c16_prelu.yml

## ecbsr-m4c16-x4-prelu
python train.py --config ./configs/ecbsr_x4_m4c16_prelu.yml

Hardware deployment

Frontend conversion

We provide convertor for model conversion to different frontend, e.g. onnx/pb/tflite. We currently developed and tested the model with only one-channel(Y out of Ycbcr). Since the internal data-layout are quite different between tf(NHWC) and pytorch(NCHW), espetially for the pixelshuffle operation. Care must be taken to handle the data-layout, if you want to extend the pytorch-based training framework to RGB input data and deploy it on tensorflow. Follow are the demo scripts for model conversion to specific frontend:

bash
## convert the trained pytorch model to onnx with plain-topology.
python convert.py --config xxx.yml --target_frontend onnx --output_folder XXX --inp_n 1 --inp_c 1 --inp_h 270 --inp_w 480

## convert the trained pytorch model to pb-1.x with plain-topology.
python convert.py --config xxx.yml --target_frontend pb-1.x --output_folder XXX --inp_n 1 --inp_c 1 --inp_h 270 --inp_w 480

## convert the trained pytorch model to pb-ckpt with plain-topology
python convert.py --config xxx.yml --target_frontend pb-ckpt --output_folder XXX --inp_n 1 --inp_c 1 --inp_h 270 --inp_w 480

AI-Benchmark

You can download the newest version of evaluation tool from AI-Benchmark. Then you can install the app via ADB tools,

adb install -r [name-of-ai-benchmar].apk

MNN (Come soon!)

For universal CPU & GPU of mobile hardware implementation.

RKNN (Come soon!)

For NPU inplementation of Rockchip hardware, e.g. RK3399Pro/RK1808.

MiniNet (Come soon!)

A super light-weight CNN inference framework implemented by us, with only conv-3x3, element-wise op, ReLU(PReLU) activations, and pixel-shuffle for common super resolution task. For more details, please refer to /ECBSR/deploy/mininet

Quantization tools (Come soon!)

For fixed-arithmetic quantization of image super resolution.

Citation


bibtex
@inproceedings{zhang2021edge,
  title={Edge-oriented Convolution Block for Real-time Super Resolution on Mobile Devices},
  author={Zhang, Xindong and Zeng, Hui and Zhang, Lei},
  booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
  pages={4034--4043},
  year={2021}
}

Acknowledgement

Thanks EDSR for the pioneering work and excellent codebase! The implementation integrated with EDSR is placed on /legacy

Issues· 0 开放

查看全部 Issues在 GitHub 打开

暂无开放 Issues,或尚未同步最近议题。

> 标签

Pythonreal-timesuper-resolution

暂无评论,来聊聊你的看法吧

> 工具信息

发布日期2026年8月1日
最后更新2026年9月17日
分类编程语言
定价开源

> 相关工具

T
TypeScript
JavaScript 的超集,为前端与全栈提供静态类型
P
Python
通用编程语言,广泛用于 Web、数据与 AI
G
Go
Google 推出的简洁高效系统语言