Deepfake-vs-Real

# **Deepfake vs Real**

**Deepfake vs Real** is a dataset designed for image classification, distinguishing between deepfake and real images. This dataset includes a diverse collection of high-quality deepfake images to enhance classification accuracy and improve the model’s overall efficiency. By providing a well-balanced dataset, it aims to support the development of more robust deepfake detection models.

# **Label Mappings**
- **Mapping of IDs to Labels:** `{0: 'Deepfake', 1: 'Real'}`
- **Mapping of Labels to IDs:** `{'Deepfake': 0, 'Real': 1}`

This dataset serves as a valuable resource for training, evaluating, and benchmarking AI models in the field of deepfake detection.

# **Dataset Composition**

The **Deepfake vs Real** dataset is composed of modular subsets derived from the following datasets:

- [Deepfakes-QA-Patch1](https://huggingface.co/datasets/prithivMLmods/Deepfakes-QA-Patch1)
- [Deepfakes-QA-Patch2](https://huggingface.co/datasets/prithivMLmods/Deepfakes-QA-Patch2)

These subsets contribute to a diverse and high-quality dataset, enhancing the classification performance of deepfake detection models. By integrating multiple sources, this dataset ensures better generalization and improved robustness in distinguishing between deepfake and real images.

# **Deepfake vs Real（深度伪造与真实图像）**
**Deepfake vs Real（深度伪造与真实图像）** 是专为图像分类任务打造的数据集，核心目标为区分深度伪造（Deepfake）图像与真实图像。本数据集收录了多样化的高质量深度伪造图像，旨在提升分类精度并优化模型整体运行效率。通过提供分布均衡的数据集，其致力于支撑更具鲁棒性的深度伪造检测模型的研发。

# **标签映射（Label Mappings）**
- **ID到标签的映射关系**：`{0: '深度伪造（Deepfake）', 1: '真实图像'}`
- **标签到ID的映射关系**：`{'深度伪造（Deepfake）': 0, '真实图像': 1}`

本数据集可作为深度伪造检测领域中AI模型训练、评估与基准测试的宝贵资源。

# **数据集构成（Dataset Composition）**
**Deepfake vs Real（深度伪造与真实图像）** 数据集由以下来源的模块化子集构建而成：
- [Deepfakes-QA-Patch1](https://huggingface.co/datasets/prithivMLmods/Deepfakes-QA-Patch1)
- [Deepfakes-QA-Patch2](https://huggingface.co/datasets/prithivMLmods/Deepfakes-QA-Patch2)

这些子集共同构成了多样化且高质量的数据集，可有效提升深度伪造检测模型的分类性能。通过整合多源数据，本数据集能够在区分深度伪造图像与真实图像的任务中实现更优的泛化能力与鲁棒性。