7th place solution

Overview

SIIM-FISABIO-RSNA-COVID-19-Detection 7th place solution

Validation:

We used iterative-stratification with 5 folds (https://github.com/trent-b/iterative-stratification) stratified by study level classes and number of boxes.

Study level:

We used efficientnet-b7, v2s, v2m, and v2l with aux branches after 3 different blocks. The models were trained on 3 folds and on different image resolutions (512, 640, 768) to produce 14 classifiers.

We used simple averaging for ensembling the models. LB mAP for study level was ~41.5-41.6

Image level:

We used mmdetection library to train detectoRS50, universeNet50, and universeNet101. detectoRS50 and universeNet50 were trained on one fold, and universeNet101 was trained on each fold + pseudo labels for public data using the universeNet50 model.

WBF did not work for us, so we decided to use NMW for ensembling from https://github.com/ZFTurbo/Weighted-Boxes-Fusion.

TTA: HorizontalFlip for detectoRS and multi-scale TTA for all universeNet models on [(640, 640), (800, 800)].

Binary classifiers were trained in the same manner as study level models, 3 fold ensemble was used.

Augmentations:

Our augmentations include HorizontalFlip, RandomCrop (for study level), ShiftScaleRotate, CLAHE, RandomGamma, Cutout from albumentations library (https://albumentations.ai/ ).

How to run detector:

  1. Change the paths to your dcm pickle files in the config files for universeNet and detectoRS.
  2. The detector can be trained inside the folder UniverseNet as follows:
./tools/dist_train.sh ${CONFIG_FILE} ${GPU_NUM}

How to run classifier:

  1. To train classifier run train_normal.py. To change the data root, the dcm pickle files, and the fold number use --data_root, --dcm_folds_train, --dcm_folds_val, and --fold. The auxilary branches can be changed as well via --aux. For example:
CUDA_VISIBLE_DEVICES=0,2,3,4 python train_normal.py --scheduler plateau --fold 0 --aux 5678 --v2_size m --batch_size 32 --data_root SIIM-FISABIO-RSNA-COVID-19-Detection --dcm_folds_train /dcm_folds/data_train_dcm_fold0.pickle --dcm_folds_val /dcm_folds/data_val_dcm_fold0.pickle
Here use convulation with sobel filter from scratch in opencv python .

Here use convulation with sobel filter from scratch in opencv python .

Tamzid hasan 2 Nov 11, 2021
基于openpose和图像分类的手语识别项目

手语识别 0、使用到的模型 (1). openpose,作者:CMU-Perceptual-Computing-Lab https://github.com/CMU-Perceptual-Computing-Lab/openpose (2). 图像分类classification,作者:Bubbl

20 Dec 15, 2022
Dirty, ugly, and hopefully useful OCR of Facebook Papers docs released by Gizmodo

Quick and Dirty OCR of Facebook Papers Gizmodo has been working through the Facebook Papers and releasing the docs that they process and review. As lu

Bill Fitzgerald 2 Oct 28, 2021
Recognizing cropped text in natural images.

ASTER: Attentional Scene Text Recognizer with Flexible Rectification ASTER is an accurate scene text recognizer with flexible rectification mechanism.

Baoguang Shi 681 Jan 02, 2023
A toolbox of scene text detection and recognition

FudanOCR This toolbox contains the implementations of the following papers: Scene Text Telescope: Text-Focused Scene Image Super-Resolution [Chen et a

FudanVIC Team 170 Dec 26, 2022
A pure pytorch implemented ocr project including text detection and recognition

ocr.pytorch A pure pytorch implemented ocr project. Text detection is based CTPN and text recognition is based CRNN. More detection and recognition me

coura 444 Dec 30, 2022
pulse2percept: A Python-based simulation framework for bionic vision

pulse2percept: A Python-based simulation framework for bionic vision Retinal degenerative diseases such as retinitis pigmentosa and macular degenerati

67 Dec 29, 2022
PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector

Description This is a PyTorch Re-Implementation of EAST: An Efficient and Accurate Scene Text Detector. Only RBOX part is implemented. Using dice loss

365 Dec 20, 2022
Optical character recognition for Japanese text, with the main focus being Japanese manga

Manga OCR Optical character recognition for Japanese text, with the main focus being Japanese manga. It uses a custom end-to-end model built with Tran

Maciej Budyś 327 Jan 01, 2023
🔎 Like Chardet. 🚀 Package for encoding & language detection. Charset detection.

Charset Detection, for Everyone 👋 The Real First Universal Charset Detector A library that helps you read text from an unknown charset encoding. Moti

TAHRI Ahmed R. 332 Dec 31, 2022
A simple component to display annotated text in Streamlit apps.

Annotated Text Component for Streamlit A simple component to display annotated text in Streamlit apps. For example: Installation First install Streaml

Thiago Teixeira 312 Dec 30, 2022
Driver Drowsiness Detection with OpenCV & Dlib

In this project, we have built a driver drowsiness detection system that will detect if the eyes of the driver are close for too long and infer if the driver is sleepy or inactive.

Mansi Mishra 4 Oct 26, 2022
Drowsiness Detection and Alert System

A countless number of people drive on the highway day and night. Taxi drivers, bus drivers, truck drivers, and people traveling long-distance suffer from lack of sleep.

Astitva Veer Garg 4 Aug 01, 2022
🖺 OCR using tensorflow with attention

tensorflow-ocr 🖺 OCR using tensorflow with attention, batteries included Installation git clone --recursive http://github.com/pannous/tensorflow-ocr

646 Nov 11, 2022
CRAFT-Pyotorch:Character Region Awareness for Text Detection Reimplementation for Pytorch

CRAFT-Reimplementation Note:If you have any problems, please comment. Or you can join us weChat group. The QR code will update in issues #49 . Reimple

453 Dec 28, 2022
Solution for Problem 1 by team codesquad for AIDL 2020. Uses ML Kit for OCR and OpenCV for image processing

CodeSquad PS1 Solution for Problem Statement 1 for AIDL 2020 conducted by @unifynd technologies. Problem Given images of bills/invoices, the task was

Burhanuddin Udaipurwala 111 Nov 27, 2022
Pixie - A full-featured 2D graphics library for Python

Pixie - A full-featured 2D graphics library for Python Pixie is a 2D graphics library similar to Cairo and Skia. pip install pixie-python Features: Ty

treeform 65 Dec 30, 2022
A curated list of awesome synthetic data for text location and recognition

awesome-SynthText A curated list of awesome synthetic data for text location and recognition and OCR datasets. Text location SynthText SynthText_Chine

Tianzhong 283 Jan 05, 2023
A curated list of papers, code and resources pertaining to image composition

A curated list of resources including papers, datasets, and relevant links pertaining to image composition.

BCMI 391 Dec 30, 2022
An official PyTorch implementation of the paper "Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences", ICCV 2021.

PyTorch implementation of Learning by Aligning (ICCV 2021) This is an official PyTorch implementation of the paper "Learning by Aligning: Visible-Infr

CV Lab @ Yonsei University 30 Nov 05, 2022