A simple version for graphfpn

Overview

GraphFPN: Graph Feature Pyramid Network for Object Detection

Download graph-FPN-main.zip

For training , run:

python train.py

For test with Graph_fpn, run

python test.py

If You need COCO API for test, you can download from here.

Folder structure

${ROOT}
└── checkpoint/
└── COCO/    
│   └── coco/
│   │    ├── .config 
│   │    ├── 2017/
│   │
│   ├── downloads/
│
│
└── data_demo/
|   ├── data/
|   |    ├── coco
|   |    ├── checkpoint
|   ├── data.zip
|
├── results/
├── src/     
|   ├── configs/
|   |    ├── configs.py
|   |
|   ├── detection/
|   |    ├── datasets/
|   |    |      ├── coco.py
|   |    ├── utils/
|   |
|   ├── model/
|   ├── init_path.py
|   ├── demo.py
|   ├── train.py
|   ├── test.py
├── README.md 
└── requirements.txt

References

[1] Graph-FPN: GraphFPN: Graph Feature Pyramid Network for Object Detection

In addition, we provide more detection frameworks that can support GraphFPN

Download graph-mmdet.zip 

this code uses mmdetecion as the base framework, you can set yourself env based on mmdetection
this can simply run

sh train.sh

get the result of Contextual Graph Layers (CGL-1) in graphFPN, however, you should add other components from graph-FPN-main.zip to run the complete GraphFPN. Note that, based on the code of graph-mmdet.zip, you can easily construct the complete graph-fpn strcuture. Please reference the code of graph-FPN-main.zip.

Comments
  • 请问是Graph FPN的原作者吗?

    请问是Graph FPN的原作者吗?

    您好,这边看到了您在github仓库里发的代码中的graph-fpn-main.zip是我在去年11月份开始做的一直做到今年的一月份的一个学校project,当时您的代码还为开源,我这边自己手动尝试做了一些复现。很高兴我的代码能被您引用,可以麻烦您在readme中加入我的链接吗? https://github.com/lhcezx/Graph-FPN.git

    opened by lhcezx 4
  • About the edges in graphFPN

    About the edges in graphFPN

    How did you connect the nodes at the contextual level and hierarchical level? Did you connect the nodes in the contextual level based on K maximum similarity or did you connect a node to all the other nodes?

    opened by Lewislou 0
  • GraphFPN中输入变量的格式问题

    GraphFPN中输入变量的格式问题

    您好,我在调试fpn.py中的FPN类中遇到问题:请问变量img_metas的格式是什么?如果您能分享您的原始数据,我将十分感谢![email protected] def forward(self, inputs, img_metas): """Forward function.""" assert len(inputs) == len(self.in_channels) #sp_values = [] sp_positions = [] #sp_edges = [] for i in range(len(img_metas)): img_meta = img_metas[i] filename = img_meta['ori_filename'][0:-4:1] for scale in range(4): filename = '/data1/zhaogangming/cob_train_'+str(4**(scale))+'_superpixel/'+filename #sp_value_name = filename+'value.npy' sp_position_name = filename+'position.npy' #sp_edge_name = filename+'edge.npy' if os.path.exists(sp_position_name): sp_positions.append(np.load(sp_position_name, allow_pickle=True)) #sp_values.append(np.load(sp_value_name, allow_pickle=True)) #sp_edges.append(np.load(sp_edge_name, allow_pickle=True)) else: sp_positions.append([])

    opened by Idiom1999 2
  • 关于GraphFPN的一些细节。

    关于GraphFPN的一些细节。

    作者您好,我对您的GraphFPN 非常感兴趣,想将其用于目标检测 `,但是在阅读源码过程中遇到一些问题,我在mmdet版本的GraphFPN代码中看到有fpn,fpnv1,fpnv2以及fpnv3.请问这四个有什么区别吗。 GraphFPN

    另外我看到代码中写到 #sp_values = [] sp_positions = [] #sp_edges = [] for i in range(len(img_metas)): img_meta = img_metas[i] filename = img_meta['ori_filename'][0:-4:1] for scale in range(4): filename = '/data1/zhaogangming/cob_train_'+str(4**(scale))+'_superpixel/'+filename #sp_value_name = filename+'value.npy' sp_position_name = filename+'position.npy' #sp_edge_name = filename+'edge.npy' if os.path.exists(sp_position_name): sp_positions.append(np.load(sp_position_name, allow_pickle=True)) #sp_values.append(np.load(sp_value_name, allow_pickle=True)) #sp_edges.append(np.load(sp_edge_name, allow_pickle=True)) else: sp_positions.append([]) #sp_positions.append(np.load('/data1/zhaogangming/cob_train_1_superpixel/000000434183position.npy', allow_pickle=True)) #sp_values.append(np.load('/data1/zhaogangming/cob_train_1_superpixel/000000434183value.npy', allow_pickle=True)) #sp_edges.append(np.load('/data1/zhaogangming/cob_train_1_superpixel/000000434183edge.npy', allow_pickle=True)) 这部分代码的作用是什么。 期待您的回复

    opened by Zhangming001 9
  • How to get Multiscale Superpixel Hierarchy

    How to get Multiscale Superpixel Hierarchy

    Hello, how I can get Multiscale Superpixel Hierarchy? and how is the Superpixel Hierarchy used in graph_FeaturePyramid?

    Looking forward to your help, thank you very much.

    opened by yxecho115 2
  • Configuration environment problem

    Configuration environment problem

    Hello, I am going to run this code. There is an error while configuring the environment that I cannot resolve, the error is shown in the image below. The DGL library is already installed. How to solve it? Looking forward to your help, thank you very much. image

    opened by qmf2020 5
Owner
WorldGame
Like world and game
WorldGame
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

DLR-RM 4.7k Jan 1, 2023
Boundary IoU API (Beta version)

Boundary IoU API (Beta version) Bowen Cheng, Ross Girshick, Piotr Dollár, Alexander C. Berg, Alexander Kirillov [arXiv] [Project] [BibTeX] This API is

Bowen Cheng 177 Dec 29, 2022
[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

CC 4.4k Dec 27, 2022
YOLTv4 builds upon YOLT and SIMRDWN, and updates these frameworks to use the most performant version of YOLO, YOLOv4

YOLTv4 builds upon YOLT and SIMRDWN, and updates these frameworks to use the most performant version of YOLO, YOLOv4. YOLTv4 is designed to detect objects in aerial or satellite imagery in arbitrarily large images that far exceed the ~600×600 pixel size typically ingested by deep learning object detection frameworks.

Adam Van Etten 161 Jan 6, 2023
A PaddlePaddle version image model zoo.

Paddle-Image-Models English | 简体中文 A PaddlePaddle version image model zoo. Install Package Install by pip: $ pip install ppim Install by wheel package

AgentMaker 131 Dec 7, 2022
Notspot robot simulation - Python version

Notspot robot simulation - Python version This repository contains all the files and code needed to simulate the notspot quadrupedal robot using Gazeb

null 50 Sep 26, 2022
mmdetection version of TinyBenchmark.

introduction This project is an mmdetection version of TinyBenchmark. TODO list: add TinyPerson dataset and evaluation add crop and merge for image du

null 34 Aug 27, 2022
Official implementation of FCL-taco2: Fast, Controllable and Lightweight version of Tacotron2 @ ICASSP 2021

FCL-Taco2: Towards Fast, Controllable and Lightweight Text-to-Speech synthesis (ICASSP 2021) Paper | Demo Block diagram of FCL-taco2, where the decode

Disong Wang 39 Sep 28, 2022
Pytorch version of VidLanKD: Improving Language Understanding viaVideo-Distilled Knowledge Transfer

VidLanKD Implementation of VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer by Zineng Tang, Jaemin Cho, Hao Tan, Mohi

Zineng Tang 54 Dec 20, 2022
The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

Face Alignment in Full Pose Range: A 3D Total Solution By Jianzhu Guo. [Updates] 2020.8.30: The pre-trained model and code of ECCV-20 are made public

Jianzhu Guo 3.4k Jan 2, 2023
A modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (prediction model)

ParallelFold Author: Bozitao Zhong This is a modified version of DeepMind's Alphafold2 to divide CPU part (MSA and template searching) and GPU part (p

Bozitao Zhong 77 Dec 22, 2022
GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot

GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from GitHub.

null 2.3k Jan 9, 2023
Pytorch version of SfmLearner from Tinghui Zhou et al.

SfMLearner Pytorch version This codebase implements the system described in the paper: Unsupervised Learning of Depth and Ego-Motion from Video Tinghu

Clément Pinard 909 Dec 22, 2022
PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

About PyTorch 1.2.0 Now the master branch supports PyTorch 1.2.0 by default. Due to the serious version problem (especially torch.utils.data.dataloade

Sanghyun Son 2.1k Jan 1, 2023
Unofficial Alias-Free GAN implementation. Based on rosinality's version with expanded training and inference options.

Alias-Free GAN An unofficial version of Alias-Free Generative Adversarial Networks (https://arxiv.org/abs/2106.12423). This repository was heavily bas

dusk (they/them) 75 Dec 12, 2022
Collection of generative models in Pytorch version.

pytorch-generative-model-collections Original : [Tensorflow version] Pytorch implementation of various GANs. This repository was re-implemented with r

Hyeonwoo Kang 2.4k Dec 31, 2022
Seeing if I can put together an interactive version of 3b1b's Manim in Streamlit

streamlit-manim Seeing if I can put together an interactive version of 3b1b's Manim in Streamlit Installation I had to install pango with sudo apt-get

Adrien Treuille 6 Aug 3, 2022
A multilingual version of MS MARCO passage ranking dataset

mMARCO A multilingual version of MS MARCO passage ranking dataset This repository presents a neural machine translation-based method for translating t

null 75 Dec 27, 2022
Code and data to accompany the camera-ready version of "Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation" in EMNLP 2021

Code and data to accompany the camera-ready version of "Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation" in EMNLP 2021

Mozhdeh Gheini 16 Jul 16, 2022