자습서: PyTorch를 사용하여 흉부 X-Ray로 COVID-19 감지하기

4.6
별점
282개의 평가
제공자:
Coursera Project Network
9,017명이 이미 등록했습니다.
학습자는 이 안내 자습서에서 다음을 수행하게 됩니다.

Create custom Dataset and DataLoader in PyTorch

Train a ResNet-18 model in PyTorch to perform Image Classification

Clock2 hours
Intermediate중급
Cloud다운로드 필요 없음
Video분할 화면 동영상
Comment Dots영어
Laptop데스크톱 전용

In this 2-hour long tutorial, we will use a ResNet-18 model and train it on a COVID-19 Radiography dataset. This dataset has nearly 3000 Chest X-Ray scans which are categorized in three classes - Normal, Viral Pneumonia and COVID-19. Our objective in this tutorial is to create an image classification model that can predict Chest X-Ray scans that belong to one of the three classes with a reasonably high accuracy. Please note that this dataset, and the model that we train in the tutorial, can not be used to diagnose COVID-19 or Viral Pneumonia. We are only using this data for educational purpose. Before you attempt this tutorial, you should be familiar with programming in Python. You should also have a theoretical understanding of Convolutional Neural Networks, and optimization techniques such as gradient descent. This is a hands on, practical tutorial that focuses primarily on implementation, and not on the theory behind Convolutional Neural Networks. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.

개발할 기술

Deep LearningMachine LearningStatistical ClassificationMedical Imagingpytorch

단계별 학습

작업 영역이 있는 분할 화면으로 재생되는 동영상에서 강사는 다음을 단계별로 안내합니다.

  1. Introduction

  2. Importing Libraries

  3. Creating Custom Dataset

  4. Image Transformations

  5. Prepare DataLoader

  6. Data Visualization

  7. Creating the Model

  8. Training the Model

  9. Final Results

안내 자습서 진행 방식

작업 영역은 브라우저에 바로 로드되는 클라우드 데스크톱으로, 다운로드할 필요가 없습니다.

분할 화면 동영상에서 강사가 프로젝트를 단계별로 안내해 줍니다.

검토

자습서: PYTORCH를 사용하여 흉부 X-RAY로 COVID-19 감지하기의 최상위 리뷰

모든 리뷰 보기

자주 묻는 질문

자주 묻는 질문

궁금한 점이 더 있으신가요? 학습자 도움말 센터를 방문해 보세요.