serbeld Goto Github PK

followers: 11.0 following: 14.0 repos: 88.0 gists: 2.0

Name: Sergio Luis Beleño Díaz

Type: User

Company: Mechatronics Engineer (University of Pamplona)

Bio: Web Developer (Thermos S.A.S)

Location: Colombia

Blog: [email protected]

Dataset 4C

The Dataset4C.hdf5 file consists in 396 images in RGB scale (Information is only on one channel to avoid overtraining), divided in 4 classes. There are 277 training images, 59 validation images and 60 test images. (70% for training, 15% for validation and 15% for testing)

The images are getting from:

Kermany, Daniel & Goldbaum, Michael & Cai, Wenjia & Valentim, Carolina & Liang, Hui-Ying & Baxter, Sally & McKeown, Alex & Yang, Ge & Wu, Xiaokang & Yan, Fangbing & Dong, Justin & Prasadha, Made & Pei, Jacqueline & Ting, Magdalena & Zhu, Jie & Li, Christina & Hewett, Sierra & Dong, Jason & Ziyar, Ian & Zhang, Kang. (2018). 
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning. 
Cell. 172. 1122-1131.e9. 10.1016/j.cell.2018.02.010. 
https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia 

Joseph Paul Cohen and Paul Morrison and Lan Dao
COVID-19 image data collection, arXiv:2003.11597, 2020
https://github.com/ieee8023/covid-chestxray-dataset

hdf5 file created by:

Author: Sergio Luis Beleño Díaz
Date: 2020-04-04

The classes are:

Normal: 99
Pneumonia Vir: 99
Pneumonia Bact: 99
COVID-19: 99

Labels:

Normal ==> 0
Pneumonia Vir ==> 1
Pneumonia Bact ==> 2
COVID-19 ==> 3

Size:

(512,512,3)

Information only on one channel

How to implement it

You can find an example of implementation in the following link:

https://github.com/Serbeld/Dataset-4C/blob/master/Data_4C.ipynb

How to download it

You can download it (Information only on one channel) in the following link:

https://drive.google.com/file/d/1yLD913J3SE7drzAvnwwcv2wKAMZXIH_L/view?usp=sharing

Sergio Luis Beleño Díaz's Projects

fullpage.js

fullPage plugin by Alvaro Trigo. Create full screen pages fast and simple

gfpgan

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

hand-webcam-write-ar

Some stuff to be able to twite with one hand

hands-on-genetic-algorithms-with-python

Hands-On Genetic Algorithms with Python, Published by Packt

handy

An easy to use wrapper (OpenCV) for hand recognition

hello-world-artwork

Video exploration taking to the limits the question of what is the relationship between electronic artworks and literature, and if they can even be called that.

how_do_drones_work

A collection of scripts from my totorials

insulatordataset

Provide normal insulator images captured by UAVs and synthetic defective insulator images.

intro-to-tkinter-youtube-course

keras-yolo2

Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower is accessible at https://git.io/vF7vI (not on Windows).

keras-yolo3

Training and Detecting Objects with YOLO3

learning

Becoming 1% better at data science everyday

learning-to-code

Scripts of all resources that I use to learn to programming. 'To infinity…and beyond!'

lungmask

Automated lung segmentation in CT

map

mean Average Precision - This code evaluates the performance of your neural net for object recognition.

markdown

Fundamentos de markdown

mask_rcnn

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

minicurso-visionartificial

Este repositorio está orientado a compartir códigos que ayuden y faciliten poner en práctica conocimientos en visión artificial.

nearest-neighbor-heuristic

This repository shows how to use the nearest neighbor heuristic as a solution for Robot Tour Optimization (RTO).

opencv-python

Curso introducción a OpenCV y Python

opencv_projects

List of OpenCV projects to further increase the computer vision community. Coding in Python & C++(In progress).

page.io

Prueba

platzinodejs

This repository is dedicated to programming practices using Node Js. These programming practices are done through Platzi's Node Js fundamentals course.