Skip to content

GitLab

Switch branch/tag
Find file Normal viewHistoryPermalink
ocrvqa.py 1.99 KB
Newer Older
renzhc's avatar
first commit  
renzhc committed
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 
# data settings

data_preprocessor = dict(
    mean=[122.770938, 116.7460125, 104.09373615],
    std=[68.5005327, 66.6321579, 70.32316305],
    to_rgb=True,
)

train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='RandomResizedCrop',
        scale=384,
        interpolation='bicubic',
        backend='pillow'),
    dict(type='CleanCaption', keys=['question', 'gt_answer']),
    dict(
        type='PackInputs',
        algorithm_keys=['question', 'gt_answer', 'gt_answer_weight'],
        meta_keys=[],
    ),
]

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='Resize',
        scale=(480, 480),
        interpolation='bicubic',
        backend='pillow'),
    dict(type='CleanCaption', keys=['question', 'gt_answer']),
    dict(
        type='PackInputs',
        algorithm_keys=['question', 'gt_answer', 'gt_answer_weight'],
        meta_keys=[],
    ),
]

train_dataloader = dict(
    batch_size=16,
    num_workers=8,
    dataset=dict(
        type='OCRVQA',
        data_root='data/ocrvqa',
        data_prefix='images',
        ann_file='annotations/dataset.json',
        split='train',
        pipeline=train_pipeline),
    sampler=dict(type='DefaultSampler', shuffle=True),
    persistent_workers=True,
    drop_last=True,
)

val_dataloader = dict(
    batch_size=64,
    num_workers=8,
    dataset=dict(
        type='OCRVQA',
        data_root='data/ocrvqa',
        data_prefix='images',
        ann_file='annotations/dataset.json',
        split='val',
        pipeline=test_pipeline),
    sampler=dict(type='DefaultSampler', shuffle=False),
    persistent_workers=True,
)
val_evaluator = dict(type='VQAAcc')

test_dataloader = dict(
    batch_size=64,
    num_workers=8,
    dataset=dict(
        type='OCRVQA',
        data_root='data/ocrvqa',
        data_prefix='images',
        ann_file='annotations/dataset.json',
        split='test',
        pipeline=test_pipeline),
    sampler=dict(type='DefaultSampler', shuffle=False),
)
test_evaluator = dict(type='VQAAcc')