数据集获取

git clone https://github.com/rezacsedu/Figure1-COVID-chestxray-dataset.git

curl -L -o repo.zip https://github.com/rezacsedu/Figure1-COVID-chestxray-dataset/archive/refs/heads/master.zip
unzip repo.zip

源站 README 摘录（使用方式）

Figure 1 COVID-19 Chest X-ray Dataset Initiative

Note: The COVID-19 image data provided here are intended to be used for research purposes only, and we are working continuously to grow this dataset as new data becomes available.

Core COVID-Net Team

• DarwinAI Corp., Canada and Vision and Image Processing Research Group, University of Waterloo, Canada
  • Linda Wang
  • Alexander Wong
  • Zhong Qiu Lin
  • Paul McInnis
  • Audrey Chung
  • Hayden Gunraj, COVIDNet for CT: Coming soon.
• Vision and Image Processing Research Group, University of Waterloo, Canada
  • James Lee
• Matt Ross and Blake VanBerlo (City of London), COVID-19 Chest X-Ray Model: https://github.com/aildnont/covid-cxr
• Ashkan Ebadi (National Research Council Canada)
• Kim-Ann Git (Selayang Hospital)
• Abdul Al-Haimi
  We especially thank Figure 1 for their collaboration in compiling this medical data.
  We are building this dataset as a part of the COVIDx dataset to enhance our models for COVID-19 detection (COVID-Net) and COVID-19 risk stratification (COVID-RiskNet):
• COVID-Net: https://github.com/lindawangg/COVID-Net
• COVID-RiskNet: coming soon
  Please see the main COVID-Net repo for details on data extraction and instructions for creating the full COVIDx dataset.
  If you would like to contribute COVID-19 x-ray images, please submit them via Figure 1 here. If you have any questions, please contact us at audrey@darwinai.ca and a28wong@uwaterloo.ca or alex@darwinai.ca. Lets all work together to stop the spread of COVID-19!

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

完整仓库：github.com/rezacsedu/Figure1-COVID-chestxray-dataset