Capsule endoscopy detection DACON challenge

Related tags

Deep Learningcapsule_endoscopy_detection
Overview

capsule_endoscopy_detection (DACON Challenge)

Overview

  • Yolov5, Yolor, mmdetection기반의 모델을 사용 (총 11개 모델 앙상블)
    • 모든 모델은 학습 시 Pretrained Weight을 yolov5, yolor, mmdetection 및 swin transformer github로부터 받아서 사용
    • 각 방식에 필요한 형태로 데이터의 format 변경
  • Train set과 Validation set을 나누어 진행
  • 총 11개의 결과를 앙상블
    • detectors_casacde_rcnn_resnet50_multiscale, retinanet_swin-l, retinanet_swin-l_multiscale, retinanet_swin-t, atss_swin-l_multiscale, faster_rcnn-swin-l_multiscale, yolor_tta_multiscale, yolov5x, yolov5x_tta, yolov5x_tta_multiscale
    • Weighted boxes fusion (WBF) 방식으로 앙상블 진행 (Iou threshold = 0.4)
    • 모델에 관한 보다 자세한 내용은 /all_steps 폴더 내에 STEP2로 시작하는 .sh 스크립트들에 적힌 주석을 참고해주세요!

환경(env) 세팅

  • 실험 환경: Ubuntu 18.04, Cuda 11.3, Anaconda3, Python 3.8
  1. git clone ( + 폴더 권한 설정)
git clone https://github.com/MAILAB-Yonsei/capsule_endoscopy_detection.git
chmod -R 777 capsule_endoscopy_detection
cd capsule_endoscopy_detection
  1. cbnet만 제외한 나머지에 대한 env 생성 (all_except_cbnet)
conda create -n all_except_cbnet python=3.8
conda activate all_except_cbnet
pytorch 설치 (ex. conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch)
pip install openmim
mim install mmdet
pip install -r requirements_all_except_cbnet.txt
conda deactivate
  1. cbnet에 대한 env 생성 (cbnet)
conda create -n cbnet python=3.8
conda activate cbnet
pytorch 설치 (ex. conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch)
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cu_version}/{torch_version}/index.html
     (ex. pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.10.0/index.html)
cd UniverseNet
pip install -r requirements/build.txt
pip install -v -e .  # or "python setup.py develop"
pip install instaboostfast
pip install git+https://github.com/cocodataset/panopticapi.git
pip install git+https://github.com/lvis-dataset/lvis-api.git
pip install albumentations>=0.3.2 --no-binary imgaug,albumentations
pip install pandas
pip install tqdm
pip install shapely
conda deactivate
cd ..

main code 실행

[각 STEP 별로 자세한 설명은 /all_steps 폴더 내의 각각의 .sh 파일에 적힌 주석을 참고해주세요!]

STEP0. data root path 지정

cd all_steps
gedit data_path.txt

data_path.txt 파일에 data의 절대 경로를 명시한다!!! (ex. /mnt/data)

STEP1. data preparation (약 20~30분 소요)

conda activate all_except_cbnet
bash STEP1_data_preparation.sh

STEP2. 각 모델을 학습시킨다. (pretrained 모델로 inference만 하고자 한다면 바로 STEP3로!)

  • cbnet만 제외한 나머지에 대한 Training
conda activate all_except_cbnet
bash STEP2_train_model1_atss_swin-l_ms.sh
bash STEP2_train_model2_detectors_cascade_rcnn_r50_ms.sh
bash STEP2_train_model3_faster_rcnn_swin-l_ms.sh
bash STEP2_train_model4_retinanet_swin-l.sh
bash STEP2_train_model5_retinanet_swin-l_ms.sh
bash STEP2_train_model6_retinanet_swin-t_ms.sh
bash STEP2_train_model7_yolor.sh
bash STEP2_train_model8_yolo5x.sh
  • cbnet에 대한 Training
conda activate cbnet
bash STEP2_train_model9_cbnet_faster_rcnn_swin-l_ms.sh

STEP3. 모든 모델에 대해 Inference를 진행한다. (모델 하나당 20~30분 소요)

  • STEP2.를 건너뛰고 pretrained 모델에 대해 test를 하는 경우 아래 과정을 수행한 뒤 STEP3.의 명령어를 실행:
    • 아래의 weight 파일 링크에서 받은 mmdetection/ckpts 폴더를 /mmdetection 폴더 아래에 위치시킨다.
    • 아래의 weight 파일 링크에서 받은 UniverseNet/ckpts 폴더를 /UniverseNet 폴더 아래에 위치시킨다.
    • 아래의 weight 파일 링크에서 받은 YOLO/ckpts 폴더를 /YOLO 폴더 아래에 위치시킨다.
    • weight 파일 링크: https://drive.google.com/drive/folders/151KJC3FTUsK5mfx4TtNbhiFuuvLIeGz-?usp=sharing
  • cbnet만 제외한 나머지에 대한 Inference
conda activate all_except_cbnet
bash STEP3_inference_all_except_cbnet.sh
  • cbnet에 대한 Inference
conda activate cbnet
bash STEP3_inference_cbnet.sh

SETP4. 모든 모델에 대해 앙상블을 진행한다.

conda activate all_except_cbnet
bash STEP4_ensemble.sh
  • 최종 파일은 가장 상위 디렉토리에 'final.csv'로 생성!!!

주의사항

모두 순서에 맞게 코드를 구성해놓았기 때문에 하나의 코드를 2번 실행하는 등의 경우 진행에 어려움이 있을 수 있습니다. 참고해주세요.

현재 코드는 validation은 진행하지 않게 주석처리했습니다. 원하시면 predict.py에서 validation 주석처리를 풀고 val_answer.csv 파일의 경로를 설정해주시면 됩니다.

(predict.py 파일 위치: /mmdetection/predict/main.py, /UniverseNet/predict/main.py)

Owner
MAILAB
Medical Artificial Intelligence Laboratory at Yonsei University, Republic of Korea
MAILAB
GitHub Repository
Weight initialization schemes for PyTorch nn.Modules

nninit Weight initialization schemes for PyTorch nn.Modules. This is a port of the popular nninit for Torch7 by @kaixhin. ##Update This repo has been

Alykhan Tejani 69 Jan 26, 2021
Implemented fully documented Particle Swarm Optimization algorithm (basic model with few advanced features) using Python programming language

Implemented fully documented Particle Swarm Optimization (PSO) algorithm in Python which includes a basic model along with few advanced features such as updating inertia weight, cognitive, social lea

9 Nov 29, 2022
This repository contains code and data for "On the Multimodal Person Verification Using Audio-Visual-Thermal Data"

trimodal_person_verification This repository contains the code, and preprocessed dataset featured in "A Study of Multimodal Person Verification Using

ISSAI 7 Aug 31, 2022
A PaddlePaddle implementation of Time Interval Aware Self-Attentive Sequential Recommendation.

TiSASRec.paddle A PaddlePaddle implementation of Time Interval Aware Self-Attentive Sequential Recommendation. Introduction 论文：Time Interval Aware Sel

Paddorch 2 Nov 28, 2021
[CVPR 2021] Region-aware Adaptive Instance Normalization for Image Harmonization

RainNet — Official Pytorch Implementation Region-aware Adaptive Instance Normalization for Image Harmonization Jun Ling, Han Xue, Li Song*, Rong Xie,

130 Dec 11, 2022
Mail classification with tensorflow and MS Exchange Server (ham or spam).

Mail classification with tensorflow and MS Exchange Server (ham or spam).

Metin Karatas 1 Sep 11, 2021
Generate Cartoon Images using Generative Adversarial Network

AvatarGAN ✨ Generate Cartoon Images using DC-GAN Deep Convolutional GAN is a generative adversarial network architecture. It uses a couple of guidelin

Aakash Jhawar 50 Dec 29, 2022
This is the repository for our paper Ditch the Gold Standard: Re-evaluating Conversational Question Answering

Ditch the Gold Standard: Re-evaluating Conversational Question Answering This is the repository for our paper Ditch the Gold Standard: Re-evaluating C

Princeton Natural Language Processing 38 Dec 16, 2022
Self-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)

Self-Supervised Pillar Motion Learning for Autonomous Driving Chenxu Luo, Xiaodong Yang, Alan Yuille Self-Supervised Pillar Motion Learning for Autono

QCraft 101 Dec 05, 2022
ComputerVision - This repository aims at realized easy network architecture

ComputerVision This repository aims at realized easy network architecture Colori

DongDong 4 Dec 14, 2022
Deep Learning & 3D Convolutional Neural Networks for Speaker Verification

TensorFlow implementation of 3D Convolutional Neural Networks for Speaker Verification - Official Project Page - Pytorch Implementation This repositor

Amirsina Torfi 753 Dec 17, 2022
Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Coming soon!

ToxiChat Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Install depen

Ashutosh Baheti 11 Jan 01, 2023
A style-based Quantum Generative Adversarial Network

Style-qGAN A style based Quantum Generative Adversarial Network (style-qGAN) model for Monte Carlo event generation. Tutorial We have prepared a noteb

9 Nov 24, 2022
Unofficial implementation of Google's FNet: Mixing Tokens with Fourier Transforms

FNet: Mixing Tokens with Fourier Transforms Pytorch implementation of Fnet : Mixing Tokens with Fourier Transforms. Citation: @misc{leethorp2021fnet,

Rishikesh (ऋषिकेश) 218 Jan 05, 2023
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Faster R-CNN and Mask R-CNN in PyTorch 1.0 maskrcnn-benchmark has been deprecated. Please see detectron2, which includes implementations for all model

Facebook Research 9k Jan 04, 2023
Streamlit Tutorial (ex: stock price dashboard, cartoon-stylegan, vqgan-clip, stylemixing, styleclip, sefa)

Streamlit Tutorials Install pip install streamlit Run cd [directory] streamlit run app.py --server.address 0.0.0.0 --server.port [your port] # http:/

Jihye Back 30 Jan 06, 2023
Data augmentation for NLP, accepted at EMNLP 2021 Findings

AEDA: An Easier Data Augmentation Technique for Text Classification This is the code for the EMNLP 2021 paper AEDA: An Easier Data Augmentation Techni

Akbar Karimi 81 Dec 09, 2022
A Python package for faster, safer, and simpler ML processes

Bender 🤖 A Python package for faster, safer, and simpler ML processes. Why use bender? Bender will make your machine learning processes, faster, safe

Otovo 6 Dec 13, 2022
Robotics with GPU computing

Robotics with GPU computing Cupoch is a library that implements rapid 3D data processing for robotics using CUDA. The goal of this library is to imple

Shirokuma 625 Jan 07, 2023
Fully Convolutional DenseNet (A.K.A 100 layer tiramisu) for semantic segmentation of images implemented in TensorFlow.

FC-DenseNet-Tensorflow This is a re-implementation of the 100 layer tiramisu, technically a fully convolutional DenseNet, in TensorFlow (Tiramisu). Th

Hasnain Raza 121 Oct 12, 2022