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

Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling"

RNN-for-Joint-NLU Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling"

Kim SungDong 194 Dec 28, 2022
Source Code of NeurIPS21 paper: Recognizing Vector Graphics without Rasterization

YOLaT-VectorGraphicsRecognition This repository is the official PyTorch implementation of our NeurIPS-2021 paper: Recognizing Vector Graphics without

Microsoft 49 Dec 20, 2022
retweet 4 satoshi ⚡️

rt4sat retweet 4 satoshi This bot is the codebase for https://twitter.com/rt4sat please feel free to create an issue if you saw any bugs basically thi

6 Sep 30, 2022
This repo is for segmentation of T2 hyp regions in gliomas.

T2-Hyp-Segmentor This repo is for segmentation of T2 hyp regions in gliomas. By downloading the model from here you can use it to segment your T2w ima

1 Jan 18, 2022
PyTorch implementation of the TTC algorithm

Trust-the-Critics This repository is a PyTorch implementation of the TTC algorithm and the WGAN misalignment experiments presented in Trust the Critic

0 Nov 29, 2021
The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing".

BMC The code for the NSDI'21 paper "BMC: Accelerating Memcached using Safe In-kernel Caching and Pre-stack Processing". BibTex entry available here. B

Orange 383 Dec 16, 2022
PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Convolutions for Action Recognition"

R2Plus1D-PyTorch PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal

Irhum Shafkat 342 Dec 16, 2022
Additional functionality for use with fastai’s medical imaging module

fmi Adding additional functionality to fastai's medical imaging module To learn more about medical imaging using Fastai you can view my blog Install g

14 Oct 31, 2022
Continuous Augmented Positional Embeddings (CAPE) implementation for PyTorch

PyTorch implementation of Continuous Augmented Positional Embeddings (CAPE), by Likhomanenko et al. Enhance your Transformer positional embeddings with easy-to-use augmentations!

Guillermo Cámbara 26 Dec 13, 2022
This is a repository for a No-Code object detection inference API using the OpenVINO. It's supported on both Windows and Linux Operating systems.

OpenVINO Inference API This is a repository for an object detection inference API using the OpenVINO. It's supported on both Windows and Linux Operati

BMW TechOffice MUNICH 68 Nov 24, 2022
Avatarify Python - Avatars for Zoom, Skype and other video-conferencing apps.

Avatarify Python - Avatars for Zoom, Skype and other video-conferencing apps.

Ali Aliev 15.3k Jan 05, 2023
Pytorch Implementation for (STANet+ and STANet)

Pytorch Implementation for (STANet+ and STANet) V2-Weakly Supervised Visual-Auditory Saliency Detection with Multigranularity Perception (arxiv), pdf:

GuotaoWang 14 Nov 29, 2022
Codebase for ECCV18 "The Sound of Pixels"

Sound-of-Pixels Codebase for ECCV18 "The Sound of Pixels". *This repository is under construction, but the core parts are already there. Environment T

Hang Zhao 318 Dec 20, 2022
Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation

TVT Code of TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation Datasets: Digit: MNIST, SVHN, USPS Object: Office, Office-Home, Vi

37 Dec 15, 2022
Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing

Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing Paper Introduction Multi-task indoor scene understanding is widely considered a

62 Dec 05, 2022
This is a re-implementation of TransGAN: Two Pure Transformers Can Make One Strong GAN (CVPR 2021) in PyTorch.

TransGAN: Two Transformers Can Make One Strong GAN [YouTube Video] Paper Authors: Yifan Jiang, Shiyu Chang, Zhangyang Wang CVPR 2021 This is re-implem

Ahmet Sarigun 79 Jan 05, 2023
DLL: Direct Lidar Localization

DLL: Direct Lidar Localization Summary This package presents DLL, a direct map-based localization technique using 3D LIDAR for its application to aeri

Service Robotics Lab 127 Dec 16, 2022
MWPToolkit is a PyTorch-based toolkit for Math Word Problem (MWP) solving.

MWPToolkit is a PyTorch-based toolkit for Math Word Problem (MWP) solving. It is a comprehensive framework for research purpose that integrates popular MWP benchmark datasets and typical deep learnin

119 Jan 04, 2023
HyperLib: Deep learning in the Hyperbolic space

HyperLib: Deep learning in the Hyperbolic space Background This library implements common Neural Network components in the hypberbolic space (using th

105 Dec 25, 2022
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate. Website • Key Features • How To Use • Docs •

Pytorch Lightning 21.1k Jan 01, 2023