Spaces:
Sleeping
Sleeping
File size: 2,153 Bytes
9bf4bd7 |
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 |
_base_ = [
'_base_dbnet_resnet18_fpnc.py',
'../_base_/datasets/totaltext.py',
'../_base_/default_runtime.py',
'../_base_/schedules/schedule_sgd_1200e.py',
]
train_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadOCRAnnotations',
with_polygon=True,
with_bbox=True,
with_label=True,
),
dict(type='FixInvalidPolygon', min_poly_points=4),
dict(
type='TorchVisionWrapper',
op='ColorJitter',
brightness=32.0 / 255,
saturation=0.5),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5],
dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
dict(type='RandomCrop', min_side_ratio=0.1),
dict(type='Resize', scale=(640, 640), keep_ratio=True),
dict(type='Pad', size=(640, 640)),
dict(
type='PackTextDetInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape'))
]
test_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(type='Resize', scale=(1333, 736), keep_ratio=True),
dict(
type='LoadOCRAnnotations',
with_polygon=True,
with_bbox=True,
with_label=True,
),
dict(type='FixInvalidPolygon', min_poly_points=4),
dict(
type='PackTextDetInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape', 'scale_factor'))
]
# dataset settings
totaltext_textdet_train = _base_.totaltext_textdet_train
totaltext_textdet_test = _base_.totaltext_textdet_test
totaltext_textdet_train.pipeline = train_pipeline
totaltext_textdet_test.pipeline = test_pipeline
train_dataloader = dict(
batch_size=16,
num_workers=16,
pin_memory=True,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=totaltext_textdet_train)
val_dataloader = dict(
batch_size=1,
num_workers=1,
pin_memory=True,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=totaltext_textdet_test)
test_dataloader = val_dataloader
auto_scale_lr = dict(base_batch_size=16)
|