All Projects → lin-honghui → Huawei_DIGIX_ImageRetri_Top2

lin-honghui / Huawei_DIGIX_ImageRetri_Top2

Licence: other
2020 DIGIX GLOBAL AI CHALLENGE - Digital Device Image Retrieval - Top2 WEARE队

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Projects that are alternatives of or similar to Huawei DIGIX ImageRetri Top2

Pytorch Image Retrieval
A PyTorch framework for an image retrieval task including implementation of N-pair Loss (NIPS 2016) and Angular Loss (ICCV 2017).
Stars: ✭ 203 (+222.22%)
Mutual labels:  image-retrieval
Openunreid
PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.
Stars: ✭ 250 (+296.83%)
Mutual labels:  image-retrieval
proxy-synthesis
Official PyTorch implementation of "Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning" (AAAI 2021)
Stars: ✭ 30 (-52.38%)
Mutual labels:  image-retrieval
Retrieval 2017 Cam
Class-Weighted Convolutional Features for Image Retrieval (BMVC 2017)
Stars: ✭ 219 (+247.62%)
Mutual labels:  image-retrieval
University1652 Baseline
ACM Multimedia2020 University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization 🚁 annotates 1652 buildings in 72 universities around the world.
Stars: ✭ 232 (+268.25%)
Mutual labels:  image-retrieval
SegSwap
(CVPRW 2022) Learning Co-segmentation by Segment Swapping for Retrieval and Discovery
Stars: ✭ 46 (-26.98%)
Mutual labels:  image-retrieval
Semantic Embeddings
Hierarchy-based Image Embeddings for Semantic Image Retrieval
Stars: ✭ 196 (+211.11%)
Mutual labels:  image-retrieval
LabelRelaxation-CVPR21
Official PyTorch Implementation of Embedding Transfer with Label Relaxation for Improved Metric Learning, CVPR 2021
Stars: ✭ 37 (-41.27%)
Mutual labels:  image-retrieval
Delf Pytorch
PyTorch Implementation of "Large-Scale Image Retrieval with Attentive Deep Local Features"
Stars: ✭ 245 (+288.89%)
Mutual labels:  image-retrieval
ImageRetrieval
Content Based Image Retrieval Techniques (e.g. knn, svm using MatLab GUI)
Stars: ✭ 51 (-19.05%)
Mutual labels:  image-retrieval
Image Text Embedding
TOMM2020 Dual-Path Convolutional Image-Text Embedding https://arxiv.org/abs/1711.05535
Stars: ✭ 223 (+253.97%)
Mutual labels:  image-retrieval
Person reid baseline pytorch
Pytorch ReID: A tiny, friendly, strong pytorch implement of object re-identification baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial
Stars: ✭ 2,963 (+4603.17%)
Mutual labels:  image-retrieval
CIRR
Official repository of ICCV 2021 - Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models
Stars: ✭ 65 (+3.17%)
Mutual labels:  image-retrieval
Caffe Deepbinarycode
Supervised Semantics-preserving Deep Hashing (TPAMI18)
Stars: ✭ 206 (+226.98%)
Mutual labels:  image-retrieval
cisip-FIRe
Fast Image Retrieval (FIRe) is an open source project to promote image retrieval research. It implements most of the major binary hashing methods to date, together with different popular backbone networks and public datasets.
Stars: ✭ 40 (-36.51%)
Mutual labels:  image-retrieval
Deep Fashion Retrieval
Simple image retrival on deep-fashion dataset with pytorch - A course project
Stars: ✭ 197 (+212.7%)
Mutual labels:  image-retrieval
Sola
Scene search On Liresolr for Animation. (and video)
Stars: ✭ 253 (+301.59%)
Mutual labels:  image-retrieval
Image-Retrieval
Image retrieval program made in Tensorflow supporting VGG16, VGG19, InceptionV3 and InceptionV4 pretrained networks and own trained Convolutional autoencoder.
Stars: ✭ 56 (-11.11%)
Mutual labels:  image-retrieval
natural-language-joint-query-search
Search photos on Unsplash based on OpenAI's CLIP model, support search with joint image+text queries and attention visualization.
Stars: ✭ 143 (+126.98%)
Mutual labels:  image-retrieval
Landmark-Retrival
Easy Landmark Image Recognition with TensorFlow Hub DELF Module
Stars: ✭ 20 (-68.25%)
Mutual labels:  image-retrieval

Huawei_DIGIX_ImgRetri_Top2

2020 DIGIX GLOBAL AI CHALLENGE - Digital Device Image Retrieval - WEARE队 亚军

0. 环境&依赖

环境:

  • Ubuntu 16.04
  • CUDA 10.1 CUDNN 7.6.4
  • 1080Ti or V100
  • 内存128G

本项目所有实验均为单卡运行,使用1080Ti时batchsize改为 8(类)x 4(张)

依赖:

# 训练环境
conda env create -f env.yaml
conda activate pytorch

# 后处理
cd indexing/PyRetri-master
python setup.py install

1. 数据预处理

# 训练数据生成
root_dir="./data" # 数据集所在目录
save_dir="./data" 
patch=640

cd features/utils
python convert_jpg2npy.py -root_dir $root_dir -save_dir $save_dir -patch $patch

2. 文件目录

本项目部分代码参考开源仓库 reid-strong-baselinefast-reidPyRetri

.
├── prepare.sh (依赖包安装、数据预处理)
├── features
│   ├── checkpoints (保存训练过程权重)
│   ├── configs     (配置文件)
│   ├── data
│   ├── engine
│   ├── exp         (特征保存目录)
│   ├── log
│   ├── model
│   ├── README.md
│   ├── solver
│   ├── tools
│   └── utils
├── indexing
│   ├── features
│   ├── index_configs (特征检索配置文件)
│   ├── index_tools
│   ├── PyRetri-master
│   ├── README.md
│   ├── result_tmp    (检索结果保存目录)
│   └── trans_index_json.sh (特征检索启动文件)
└── env.yaml

3. 算法说明

详细方案请见 zhihu

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].