The project was to detect traffic signs, based on the Megengine framework.

Overview

trafficsign

赛题

旷视AI智慧交通开源赛道,初赛1/177,复赛1/12。
本赛题为复杂场景的交通标志检测,对五种交通标志进行识别。

框架

megengine

算法方案

  • 网络框架

    • atss + resnext101_32x8d
  • 训练阶段

    • 图片尺寸
      最终提交版本输入图片尺寸为(1500,2100)

    • 多尺度训练(最终提交版本未采用)
      起初我们将短边设为(1024, 1056, 1088, 1120, 1152, 1184, 1216, 1248, 1280, 1312, 1344, 1376, 1408),随机选取短边后,长边按比例缩放,并使长边长度小于1800,从而进行多尺度训练,取得了很好的效果。 不过后期的mosaic和mixup在增强时对图片进行了缩放,实则隐含了多尺度训练,且效果优于上述方法,所以我们最终去掉了多尺度训练。

    • 数据增强

      • mosaic增强

        随机选择四张图片,对图片进行随机平移10%,尺度缩放(0.5,2.0),shear 0.1,最后将四张图片进行组合。

      • mixup增强

        随机选取两张图进行叠加,我们最终选用的比例是0.5 * 原图+0.5 * 新图片,同时其进行缩放(0.5,2.0)。

        下图为mosaic+mixup示例图:

        mosaic+mixup

      • 随机水平翻转

        直接对图片进行翻转,会导致第三个类别“arr_l”(左转线)和右转线混淆,故我们添加了class-aware的翻转,遇到有“arr_l”类的图片则不进行翻转。

      • 基于Albumentations库的各种增强(最终提交版本未采用)

        我们尝试了ShiftScaleRotate(验证集+0.5)、CLANE(验证集+1.0)、RandomBrightnessContrast等,但组合起来测试集提点欠佳,所以最后没用。

      • gridmask增强(最终提交版本未采用)

        生成一个和原图相同分辨率的mask(每个grid上全为0或全为1),然后将该mask与原图相乘得到一个图像。提点欠佳,所以没采用。

      • 类别平衡采样(最终提交版本未采用)

        使用类别平衡采样后,效果不是很好,这可能是因为数据集本身没有严重的类别不均衡。下面是我们统计的每个类别在图片中出现的频率。

        红灯 直行线 左转线 禁止行驶 禁止停车
        频率 0.356 0.228 0.201 0.257 0.485
  • 多尺度测试

    • 多尺度测试图片尺寸

      最后提交版本(2100,2700),(2100,2800),(2400,3200),如果继续增加尺度,map还会继续提高。

    • topk—nms

      对上述三个尺度生成的结果先进行nms,再将得到的结果框与剩下所有框进行topk—nms(保留与当前结果框iou大于0.85的topk的框,把这些框的坐标进行融合),参数设置vote_thresh=0.85, k=5。

  • 网络结构

    • 加上增强后,backbone从res50到res101再到resx101有稳定涨点。

    • 我们还在backbone部分尝试了dcn和gcnet,验证集收效甚微,最终没有采用。

模型训练与测试

  • 数据集位置
/path/to/ 
    |->traffic   
    |    |images     
    |    |annotations->|train.json     
    |    |             |val.json     
    |    |             |test.json      
  • 训练测试

在加上增强后,我们训练了36个epoch。

pip3 install --user -r requirements.txt

export PYTHONPATH=your_path/trafficsign:$PYTHONPATH

cd weights && wget https://data.megengine.org.cn/models/weights/atss_resx101_coco_2x_800size_45dot6_b3a91b36.pkl

python3 tools/train.py -n 4 -b 2 -f configs/atss_resx101_final.py -d your_datasetpath -w weights/atss_resx101_coco_2x_800size_45dot6_b3a91b36.pkl

python3 tools/test_final.py -n 4 -se 35 -f configs/atss_resx101_final.py -d your_datasetpath 

(-n 能抢到几张卡就写几吧qaq)

备注

以上提到的所有方法,无论最终是否采用,代码中均有实现。

感谢

https://github.com/MegEngine/Models/tree/master/official/vision/detection

https://github.com/MegEngine/YOLOX

TorchOk - The toolkit for fast Deep Learning experiments in Computer Vision

TorchOk - The toolkit for fast Deep Learning experiments in Computer Vision

52 Dec 23, 2022
Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation.

Pretrain-Recsys This is our Tensorflow implementation for our WSDM 2021 paper: Bowen Hao, Jing Zhang, Hongzhi Yin, Cuiping Li, Hong Chen. Pre-Training

30 Nov 14, 2022
Official Pytorch implementation of the paper: "Locally Shifted Attention With Early Global Integration"

Locally-Shifted-Attention-With-Early-Global-Integration Pretrained models You can download all the models from here. Training Imagenet python -m torch

Shelly Sheynin 14 Apr 15, 2022
Code to reproduce results from the paper "AmbientGAN: Generative models from lossy measurements"

AmbientGAN: Generative models from lossy measurements This repository provides code to reproduce results from the paper AmbientGAN: Generative models

Ashish Bora 87 Oct 19, 2022
PyDEns is a framework for solving Ordinary and Partial Differential Equations (ODEs & PDEs) using neural networks

PyDEns PyDEns is a framework for solving Ordinary and Partial Differential Equations (ODEs & PDEs) using neural networks. With PyDEns one can solve PD

Data Analysis Center 220 Dec 26, 2022
PyTorch Implementation of Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation

StyleSpeech - PyTorch Implementation PyTorch Implementation of Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation. Status (2021.06.13

Keon Lee 140 Dec 21, 2022
Image-to-Image Translation in PyTorch

CycleGAN and pix2pix in PyTorch New: Please check out contrastive-unpaired-translation (CUT), our new unpaired image-to-image translation model that e

Jun-Yan Zhu 19k Jan 07, 2023
Zalo AI challenge 2021 task hum to song

Zalo AI challenge 2021 task Hum to Song pipeline: Chuẩn bị dữ liệu cho quá trình train: Sửa các file đường dẫn trong config/preprocess.yaml raw_path:

Vo Van Phuc 105 Dec 16, 2022
PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision

Learning to Generate Grounded Visual Captions without Localization Supervision This is the PyTorch implementation of our paper: Learning to Generate G

Chih-Yao Ma 41 Nov 17, 2022
Locally Constrained Self-Attentive Sequential Recommendation

LOCKER This is the pytorch implementation of this paper: Locally Constrained Self-Attentive Sequential Recommendation. Zhankui He, Handong Zhao, Zhe L

Zhankui (Aaron) He 8 Jul 30, 2022
Privacy-Preserving Machine Learning (PPML) Tutorial Presented at PyConDE 2022

PPML: Machine Learning on Data you cannot see Repository for the tutorial on Privacy-Preserving Machine Learning (PPML) presented at PyConDE 2022 Abst

Valerio Maggio 10 Aug 16, 2022
python debugger and anti-vm that checks if you're in a virtual machine or if someones trying to debug your file

Anti-Debug was made by Love ❌ code ✅ 🎉 ・What it checks for ・ Kills tools that can be used to debug your file ・ Exits if ran in vm (supports different

Rdimo 31 Aug 09, 2022
ARAE-Tensorflow for Discrete Sequences (Adversarially Regularized Autoencoder)

ARAE Tensorflow Code Code for the paper Adversarially Regularized Autoencoders for Generating Discrete Structures by Zhao, Kim, Zhang, Rush and LeCun

19 Nov 12, 2021
Scikit-learn compatible estimation of general graphical models

skggm : Gaussian graphical models using the scikit-learn API In the last decade, learning networks that encode conditional independence relationships

213 Jan 02, 2023
Deep learning with dynamic computation graphs in TensorFlow

TensorFlow Fold TensorFlow Fold is a library for creating TensorFlow models that consume structured data, where the structure of the computation graph

1.8k Dec 28, 2022
The implement of papar "Enhanced Graph Learning for Collaborative Filtering via Mutual Information Maximization"

SIGIR2021-EGLN The implement of paper "Enhanced Graph Learning for Collaborative Filtering via Mutual Information Maximization" Neural graph based Col

15 Dec 27, 2022
The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dea

MIC-DKFZ 1.2k Jan 04, 2023
BasicNeuralNetwork - This project looks over the basic structure of a neural network and how machine learning training algorithms work

BasicNeuralNetwork - This project looks over the basic structure of a neural network and how machine learning training algorithms work. For this project, I used the sigmoid function as an activation

Manas Bommakanti 1 Jan 22, 2022
Adversarial Attacks on Probabilistic Autoregressive Forecasting Models.

Attack-Probabilistic-Models This is the source code for Adversarial Attacks on Probabilistic Autoregressive Forecasting Models. This repository contai

SRI Lab, ETH Zurich 25 Sep 14, 2022
This is the official pytorch implementation of AutoDebias, an automatic debiasing method for recommendation.

AutoDebias This is the official pytorch implementation of AutoDebias, a debiasing method for recommendation system. AutoDebias is proposed in the pape

Dong Hande 77 Nov 25, 2022