Link to this sectionCityscapes8 데이터셋#

Link to this section소개#

The Ultralytics Cityscapes8 dataset is a compact semantic segmentation dataset with 8 images sampled from the Cityscapes dataset: 4 for training and 4 for validation. It is designed for rapid testing, debugging, and experimentation with YOLO semantic segmentation models and training pipelines. Its urban-scene content provides a useful pipeline check before scaling to the full Cityscapes dataset.

Cityscapes8은 전체 Cityscapes 데이터셋과 동일한 19개의 평가 클래스와 label_mapping 동작을 사용하며, YOLO26 semantic segmentation 워크플로우와 완전히 호환됩니다.

Link to this section데이터셋 구조#

Cityscapes8은 test 분할 없이 전체 데이터셋의 레이아웃을 그대로 따릅니다:

cityscapes8/
├── images/
│   ├── train/  # 4 images
│   └── val/    # 4 images
└── masks/
    ├── train/  # 4 single-channel PNG masks
    └── val/    # 4 single-channel PNG masks

마스크는 masks_dir: masks 필드를 통해 이미지와 쌍을 이루며, label_mapping은 소스 Cityscapes 레이블 ID를 전체 Cityscapes 데이터셋 구조에 설명된 19개의 연속적인 훈련 ID로 변환합니다.

Ultralytics Platform의 Cityscapes8에서 모든 이미지와 segmentation 마스크를 살펴보고, 이를 클론하여 클라우드에서 훈련해 보십시오.

Link to this section데이터셋 YAML#

The Cityscapes8 dataset configuration is defined in a dataset YAML file, which specifies dataset paths, class names, and other essential metadata. You can review the official cityscapes8.yaml file in the Ultralytics GitHub repository. The YAML includes a download URL for the small packaged subset.

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# Cityscapes semantic segmentation dataset (19 classes)
# Documentation: https://docs.ultralytics.com/datasets/semantic/cityscapes8
# Example usage: yolo semantic train data=cityscapes8.yaml model=yolo26n-sem.pt
# parent
# ├── ultralytics
# └── datasets
#     └── cityscapes8 ← downloads here (small subset)
#         └── images
#         └── masks

# Dataset root directory
path: cityscapes8 # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images

masks_dir: masks # semantic mask directory

# Cityscapes 19-class labels
names:
  0: road
  1: sidewalk
  2: building
  3: wall
  4: fence
  5: pole
  6: traffic light
  7: traffic sign
  8: vegetation
  9: terrain
  10: sky
  11: person
  12: rider
  13: car
  14: truck
  15: bus
  16: train
  17: motorcycle
  18: bicycle

# Map source label IDs to train IDs; ignore_label is converted to 255.
label_mapping:
  -1: ignore_label
  0: ignore_label
  1: ignore_label
  2: ignore_label
  3: ignore_label
  4: ignore_label
  5: ignore_label
  6: ignore_label
  7: 0
  8: 1
  9: ignore_label
  10: ignore_label
  11: 2
  12: 3
  13: 4
  14: ignore_label
  15: ignore_label
  16: ignore_label
  17: 5
  18: ignore_label
  19: 6
  20: 7
  21: 8
  22: 9
  23: 10
  24: 11
  25: 12
  26: 13
  27: 14
  28: 15
  29: ignore_label
  30: ignore_label
  31: 16
  32: 17
  33: 18

# Download URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/cityscapes8.zip

Link to this section사용법#

이미지 크기 1024로 100 epochs 동안 Cityscapes8 데이터셋에서 YOLO26n-sem 모델을 학습하려면 다음 예제를 사용하십시오. 전체 학습 옵션 목록은 YOLO 학습 문서를 참조하십시오.

from ultralytics import YOLO

# Load a pretrained YOLO26n-sem model
model = YOLO("yolo26n-sem.pt")

# Train the model on Cityscapes8
results = model.train(data="cityscapes8.yaml", epochs=100, imgsz=1024)

Link to this section인용, 라이선스 및 감사의 글#

Cityscapes8은 사용자 지정 비상업적 라이선스에 따라 릴리스된 Cityscapes에서 샘플링되었습니다. 자세한 내용은 전체 Cityscapes 데이터셋 페이지를 참조하십시오.

연구 또는 개발에 Cityscapes 데이터셋을 사용하는 경우 다음 논문을 인용해 주십시오:

@inproceedings{Cordts2016Cityscapes,
  title={The Cityscapes Dataset for Semantic Urban Scene Understanding},
  author={Cordts, Marius and Omran, Mohamed and Ramos, Sebastian and Rehfeld, Timo and Enzweiler, Markus and Benenson, Rodrigo and Franke, Uwe and Roth, Stefan and Schiele, Bernt},
  booktitle={Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016}
}

Special thanks to the Cityscapes team for their ongoing contributions to the autonomous driving and computer vision communities.

Link to this sectionFAQ#

Link to this sectionUltralytics Cityscapes8 데이터셋은 어떤 용도로 사용됩니까?#

The Ultralytics Cityscapes8 dataset is designed for rapid testing and debugging of semantic segmentation models. With only 8 images (4 for training, 4 for validation), it is ideal for verifying YOLO semantic segmentation pipelines, including mask loading, augmentations, validation, and export paths, before scaling to the full Cityscapes dataset. Explore the Cityscapes8 YAML configuration for more details.

Link to this sectionCityscapes8은 전체 Cityscapes 데이터셋과 어떻게 다릅니까?#

Cityscapes8 samples 8 images (4 train, 4 val) from Cityscapes' 2,975-training/500-validation split, using the same 19 classes and label_mapping, so a pipeline that runs on Cityscapes8 runs unmodified on the full dataset — just point data= at cityscapes.yaml instead of cityscapes8.yaml. Unlike the full dataset, Cityscapes8 has no manual-download step and no test split.

Link to this sectionCityscapes8 데이터셋을 사용하여 YOLO26 모델을 훈련하려면 어떻게 해야 합니까?#

Python 또는 CLI를 사용하여 Cityscapes8에서 YOLO26 semantic segmentation 모델을 학습할 수 있습니다:

from ultralytics import YOLO

# Load a pretrained YOLO26n-sem model
model = YOLO("yolo26n-sem.pt")

# Train the model on Cityscapes8
results = model.train(data="cityscapes8.yaml", epochs=100, imgsz=1024)

추가 학습 옵션은 YOLO 학습 문서를 참조하십시오.

Link to this section벤치마킹을 위해 Cityscapes8을 사용해야 합니까?#

아니요. Cityscapes8은 모델 비교를 수행하기에는 너무 작으며, 학습 및 평가 파이프라인 점검을 위한 용도입니다. semantic segmentation에 대한 대표적인 벤치마크 결과가 필요한 경우 전체 Cityscapes 검증 세트를 사용하십시오.