Griffon Language-prompted Localization数据集是一个用于视觉问答和对象检测任务的数据集，主要语言为英语。数据集的规模在100M到1B之间。数据集包含预训练数据和指令数据，预训练数据包括Visual Genome、MSCOCO和Objects365-2023的图像和注释，指令数据包括flickr30K Entities的图像。数据集的许可证为Attribution

Hugging Face2024-07-11 更新200

Multimodal-Fatima/VQAv2_sample_test_embeddings

视觉问答

特征嵌入

--- dataset_info: features: - name: image dtype: image - name: id dtype: int64 - name: vision_embeddings sequence: float32 splits: - name: openai_clip_vit_large_patch14 num

Hugging Face2023-02-12 更新100

LambdaTests/VQAv2Validation_ViT_H_14_A_T_C_Q_benchmarks_partition_global_3_1000

视觉问答

机器学习模型

--- dataset_info: features: - name: id dtype: int64 - name: response dtype: string splits: - name: train num_bytes: 1037 num_examples: 32 download_size: 2262 dataset_size

Hugging Face2023-04-20 更新70

Multimodal-Fatima/VQAv2_validation_facebook_opt_6.7b_mode_VQAv2_visclues_detection_ns_500_open_ended

视觉问答

模型验证

--- dataset_info: features: - name: id dtype: int64 - name: question dtype: string - name: true_label sequence: string - name: prediction dtype: string splits: - name: fe

Hugging Face2023-02-23 更新100

LambdaTests/VQAv2Validation_ViT_H_14_A_T_C_Q_benchmarks_partition_global_17_1000

视觉问答

机器学习模型

--- dataset_info: features: - name: id dtype: int64 - name: response dtype: string splits: - name: train num_bytes: 897 num_examples: 32 download_size: 2022 dataset_size:

Hugging Face2023-04-20 更新90

hhenryz/Mixed_VQA_GenQA_EvalQA_1.5M

资源简介：

数据集许可证

相关数据集