AI Rank
EN
← 开源
google

hdrnet

An implementation of 'Deep Bilateral Learning for Real-Time Image Enhancement', SIGGRAPH 2017

Model DevelopmentArchitecturePython
在 GitHub 打开
增长势头
+024 小时新增 Star0.0%
877
Star
319
Fork
+0
本周
4
贡献者
创建于 2016-09-12 · 更新于 2026-10-02 · 今日第 12968 名
主要开发者
fbleibel-gmgharbitianfan-google

google/hdrnet 排名第 12,968，有 877 个星标。

同类别比较

google/hdrnet 排名第 12,968，此处有 8 个同类条目；yule-BUAA/MergeLM 排名第 12,965。

同类别比较
名称排名指标
dmlc/dmlc-core12,959
语言:
C++
星标数:
878
分叉数:
525
简介:
A common bricks library for building scalable and portable distributed machine learning.
lucidrains/RETRO-pytorch12,961
语言:
Python
星标数:
878
分叉数:
108
简介:
Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch
mystic123/tensorflow-yolo-v312,962
语言:
Python
星标数:
878
分叉数:
343
简介:
Implementation of YOLO v3 object detector in Tensorflow (TF-Slim)
yule-BUAA/MergeLM12,965
语言:
Python
星标数:
878
分叉数:
53
简介:
Codebase for Merging Language Models (ICML 2024)
EpistasisLab/pmlb12,973
语言:
Python
星标数:
876
分叉数:
144
简介:
PMLB: A large, curated repository of benchmark datasets for evaluating supervised machine learning algorithms.
WooooDyy/AgentGym-RL12,975
语言:
Python
星标数:
876
分叉数:
89
简介:
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
brownvc/R3GAN12,976
语言:
Python
星标数:
876
分叉数:
45
简介:
Code for NeurIPS 2024 paper - The GAN is dead; long live the GAN! A Modern Baseline GAN - by Huang et al.
polarisZhao/PFLD-pytorch12,984
语言:
Python
星标数:
876
分叉数:
205
简介:
PFLD pytorch Implementation
关键参数与规格
关键参数与规格
参数值
语言Python
类别Model Development
子类别Architecture
关键词Image production
星标数877
分叉数319
贡献者4
创建日期2016-09-12
更新日期2026-10-02
1 天星标数0
7 天星标数0
排名12,968
上次排名12,865
排名变化-103
7 天星标排名13,696
上次 7 天星标排名13,709
7 天星标排名变化13
总星标排名12,349
上次总星标排名12,324
总星标排名变化-25
国家USA
README 摘录

Deep Bilateral Learning for Real-Time Image Enhancements Siggraph 2017 Visit our Project Page. Hasinoff Fredo Durand Maintained by Michael Gharbi ( ) Tested on Python 2. Disclaimer This is not an official Google product. Setup Dependencies To install the Python dependencies, run: Build Our network requires a custom Tensorflow operator to "slice" in the bilateral grid. To build it, run: To build the benchmarking code, run: Note that the benchmarking code requires a frozen and optimized model. To build the Android

demo, see dedicated section below. Test Run the test suite to make sure the BilateralSlice operator works correctly: Download pretrained models We provide a set of pretrained models. One of these is included in the repo (see ). To download the rest of them run: Usage To train a model, run the following command: Look at for a typical structure of the training data folder. You can monitor the training process using Tensorboard: To run a trained model on a novel

image (or set of images), use: To prepare a model for use on mobile, freeze the graph, and optimize the network: You will need to change the environment variable in and compile the necessary tensorflow command line tools for this (automated in the script). Android prototype We will add it to this repo soon. Known issues and limitations The BilateralSliceApply operation is GPU only at this point. We do not plan on releasing a CPU implementation. The provided pre-trained

models were updated from an older version and might slightly differ from the models used for evaluation in the paper. The pre-trained HDR+ model expects as input a specially formatted 16-bit linear input. Apply lens shading correction (aka vignetting correction). Our Android demo approximates this by undoing the RGB->YUV conversion and white balance, and tone mapping performed by the Qualcomm SOC. It results in slightly different colors than that on the test set. If you run our

HDR+ model on an sRGB input, it may produce uncanny colors.

常见问题

记录了多少星标和分叉？

google/hdrnet 有 877 个星标和 319 个分叉。

仓库排名是多少？

google/hdrnet 排名第 12,968。

记录的语言和类别是什么？

google/hdrnet 有 877 个星标，语言为 Python，类别为 Model Development。

哪个仓库排名最接近？

google/hdrnet 与 yule-BUAA/MergeLM 比较，后者排名第 12,965，有 878 个星标。

README

Deep Bilateral Learning for Real-Time Image Enhancements

Siggraph 2017

Visit our Project Page.

Michael Gharbi Jiawen Chen Jonathan T. Barron Samuel W. Hasinoff Fredo Durand

Maintained by Michael Gharbi ()

Tested on Python 2.7, Ubuntu 14.0, gcc-4.8.

Disclaimer

This is not an official Google product.

Setup

Dependencies

To install the Python dependencies, run:

cd hdrnet
pip install -r requirements.txt

Build

Our network requires a custom Tensorflow operator to "slice" in the bilateral grid. To build it, run:

cd hdrnet
make

To build the benchmarking code, run:

cd benchmark
make

Note that the benchmarking code requires a frozen and optimized model. Use hdrnet/bin/scripts/optimize_graph.sh and hdrnet/bin/freeze.py to produce these.

To build the Android demo, see dedicated section below.

Test

Run the test suite to make sure the BilateralSlice operator works correctly:

cd hdrnet
py.test test

Download pretrained models

We provide a set of pretrained models. One of these is included in the repo (see pretrained_models/local_laplacian_sample). To download the rest of them run:

cd pretrained_models
./download.py

Usage

To train a model, run the following command:

./hdrnet/bin/train.py

Look at sample_data/identity/ for a typical structure of the training data folder.

You can monitor the training process using Tensorboard:

tensorboard --logdir

To run a trained model on a novel image (or set of images), use:

./hdrnet/bin/run.py

To prepare a model for use on mobile, freeze the graph, and optimize the network:

./hdrnet/bin/freeze_graph.py 
./hdrnet/bin/scripts/optimize_graph.sh

You will need to change the ${TF_BASE} environment variable in ./hdrnet/bin/scripts/optimize_graph.sh and compile the necessary tensorflow command line tools for this (automated in the script).

Android prototype

We will add it to this repo soon.

Known issues and limitations

  • The BilateralSliceApply operation is GPU only at this point. We do not plan on releasing a CPU implementation.

  • The provided pre-trained models were updated from an older version and might slightly differ from the models used for evaluation in the paper.

  • The pre-trained HDR+ model expects as input a specially formatted 16-bit linear input. In summary, starting from Bayer RAW:

    1. Subtract black level.
    2. Apply white balance channel gains.
    3. Demosaic to RGB.
    4. Apply lens shading correction (aka vignetting correction).

    Our Android demo approximates this by undoing the RGB->YUV conversion and white balance, and tone mapping performed by the Qualcomm SOC. It results in slightly different colors than that on the test set. If you run our HDR+ model on an sRGB input, it may produce uncanny colors.

排名相邻
同类项目