数据集获取

git clone https://github.com/KyeongsupChoi/MIA.git

curl -L -o repo.zip https://github.com/KyeongsupChoi/MIA/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

MIA

Chest X-ray pneumonia classifier using ResNet50 transfer learning, trained on the BIMCV-COVID19+ dataset.
Project Organization

├── data
│   ├── external                <- Data from third party sources.
│   ├── interim                 <- Intermediate data that has been transformed.
│   ├── processed               <- The final, canonical data sets for modeling.
│   └── raw                     <- The original, immutable data dump.
|
├── docs                        <- A default Sphinx project; see sphinx-doc.org for details
│
├── models                      <- Trained and serialized models, model predictions, or model summaries
│   └── final_model.keras       <- Two-phase ResNet50 transfer learning model
│
├── notebooks                   <- Jupyter notebooks for prototyping and EDA
│   └── Carmine400train.ipynb   <- ResNet50 training demo notebook
│
├── references                  <- Data dictionaries, manuals, and all other explanatory materials.
│   └── research_papers         <- Academic research papers in pdf format
│
├── reports                     <- Generated analysis as HTML, PDF, LaTeX, etc.
│   └── figures                 <- Generated graphics and figures to be used in reporting
|
├── src                         <- Source code for use in this project.
│   ├── __init__.py             <- Makes src a Python module
│   ├── config.py               <- Shared constants and configuration
│   │
│   ├── data                    <- Scripts to download or generate data
│   │   └── make_dataset.py     <- TSV→CSV filtering, balancing, and train/val/test splits
│   │
│   ├── features                <- Scripts to turn raw data into features for modeling
│   │   ├── build_features.py   <- Image loading, normalization, and class weight computation
│   │   └── create_sliced.py    <- Alternative CSV splitting utility
│   │
│   ├── models                  <- Scripts to train models and make predictions
│   │   ├── predict_model.py    <- Single and batch inference on chest X-rays
│   │   └── train_Carmine400.py <- Two-phase transfer learning trainer with cross-validation
│   │
│   └── visualization           <- Scripts to create exploratory and results oriented visualizations
│

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/KyeongsupChoi/MIA