File size: 2,045 Bytes
06c7b02
3e31e8f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
06c7b02
3e31e8f
06c7b02
3e31e8f
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
---
dataset_info:
  features:
  - name: image
    dtype: image
  - name: question_type
    dtype: string
  - name: confidence
    dtype: int32
  - name: answers
    sequence: string
  - name: answers_original
    list:
    - name: answer
      dtype: string
    - name: raw_answer
      dtype: string
    - name: answer_confidence
      dtype: string
    - name: answer_id
      dtype: int64
  - name: id_image
    dtype: int64
  - name: answer_type
    dtype: string
  - name: question_id
    dtype: int64
  - name: question
    dtype: string
  - name: id
    dtype: int64
  - name: clip_tags_ViT_L_14
    sequence: string
  - name: clip_tags_LAION_ViT_H_14_2B
    sequence: string
  - name: blip_caption_beam_5
    dtype: string
  - name: LLM_Description_gpt3_downstream_tasks_visual_genome_ViT_L_14
    sequence: string
  - name: LLM_Description_gpt3_downstream_tasks_visual_genome_LAION-ViT-H-14-2B
    sequence: string
  - name: DETA_detections_deta_swin_large_o365_coco_classes
    list:
    - name: attribute
      dtype: string
    - name: box
      sequence: float32
    - name: label
      dtype: string
    - name: location
      dtype: string
    - name: ratio
      dtype: float32
    - name: size
      dtype: string
    - name: tag
      dtype: string
  - name: DETA_detections_deta_swin_large_o365_coco_classes_caption_module_random
    list:
    - name: attribute
      dtype: string
    - name: box
      sequence: float64
    - name: captions_module
      sequence: string
    - name: captions_module_filter
      sequence: string
    - name: label
      dtype: string
    - name: location
      dtype: string
    - name: ratio
      dtype: float64
    - name: size
      dtype: string
    - name: tag
      dtype: string
  splits:
  - name: train
    num_bytes: 1686555802.0
    num_examples: 9009
  download_size: 1572400067
  dataset_size: 1686555802.0
---
# Dataset Card for "OK-VQA_train"

[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)