cyberorigin/alita

---
license: mit
---

## CyberOrigin Dataset

Our data includes information from home services, the logistics industry, and laboratory scenarios.
For more details, please refer to our [Offical Data Website](https://cyberorigin2077.github.io/)

contents of the dataset:
```
alita # dataset root path
└── data/
├── metadata_Traj01.json
├── segment_ids_Traj01.bin # for each frame segment_ids uniquely points to the segment index that frame i came from. You may want to use this to separate non-contiguous frames from different videos (transitions).
├── videos_Traj01.bin # 16x16 image patches at 15hz, each patch is vector-quantized into 2^18 possible integer values. These can be decoded into 256x256 RGB images using the provided magvit2.ckpt weights.
├── ...
└── ...
```

```json
{
"task": "ALITA",
"total_episodes": ,
"total_frames": ,
"token_dtype": "uint32",
"vocab_size": 262144,
"fps": 15,
"language_annotation": "None",
}
```

许可证：MIT

## 赛博起源数据集（CyberOrigin Dataset）
本数据集涵盖家庭服务、物流行业及实验室场景的相关数据。如需了解更多细节，请参阅我们的[官方数据网站](https://cyberorigin2077.github.io/)。

数据集内容如下：

alita # 数据集根目录
└── data/
├── metadata_Traj01.json
├── segment_ids_Traj01.bin # 该文件中，每个帧的segment_ids唯一指向其所属片段的索引，可用于分离来自不同视频的非连续帧（转场片段）
├── videos_Traj01.bin # 存储帧率为15Hz的16×16图像块，每个图像块经向量量化后可映射至2^18种可能的整数值。可通过提供的magvit2.ckpt权重文件将其解码为256×256的RGB图像
├── ...
└── ...

json
{
"任务": "ALITA",
"总片段数": ,
"总帧数": ,
"令牌数据类型（token_dtype）": "uint32",
"词汇表大小": 262144,
"帧率（fps）": 15,
"语言标注": "无"
}