erkam/clevr-with-depth-full-v2

--- dataset_info: features: - name: target_img dtype: image - name: source_img dtype: image - name: target_obj sequence: int64 - name: source_obj sequence: int64 - name: target_box sequence: sequence: float32 - name: source_box sequence: sequence: float32 - name: target_depth dtype: image - name: source_depth dtype: image - name: target_tri sequence: sequence: int64 - name: source_tri sequence: sequence: int64 - name: pos_prompt dtype: string - name: neg_prompt dtype: string splits: - name: test num_bytes: 43042513.0 num_examples: 300 - name: val num_bytes: 43023361.0 num_examples: 300 - name: train num_bytes: 200465105.0 num_examples: 1400 download_size: 283955264 dataset_size: 286530979.0 --- # Dataset Card for "clevr-with-depth-full-v2" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

原始信息汇总

数据集概述

数据集名称

clevr-with-depth-full-v2

数据集特征

• target_img: 图像数据类型
• source_img: 图像数据类型
• target_obj: 整数序列数据类型
• source_obj: 整数序列数据类型
• target_box: 浮点数序列数据类型
• source_box: 浮点数序列数据类型
• target_depth: 图像数据类型
• source_depth: 图像数据类型
• target_tri: 整数序列数据类型
• source_tri: 整数序列数据类型
• pos_prompt: 字符串数据类型
• neg_prompt: 字符串数据类型

数据集分割

• train: 1400个样本，占用200465105字节
• val: 300个样本，占用43023361字节
• test: 300个样本，占用43042513字节

数据集大小

• 下载大小: 283955264字节
• 数据集总大小: 286530979字节