[TODO] Remove det&recog pipelines

pull/1178/head
jiangqing.vendor 2022-07-14 09:39:40 +00:00 committed by gaotongxiao
parent 3734527d38
commit 2b3a4fe6b5
14 changed files with 0 additions and 923 deletions

View File

@ -1,88 +0,0 @@
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline_r18 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5],
dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
dict(type='EastRandomCrop', target_size=(640, 640)),
dict(type='DBNetTargets', shrink_ratio=0.4),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=['gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'],
visualize=dict(flag=False, boundary_key='gt_shrink')),
dict(
type='Collect',
keys=['img', 'gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'])
]
test_pipeline_1333_736 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 736), # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
# for dbnet_r50dcnv2_fpnc
img_norm_cfg_r50dcnv2 = dict(
mean=[122.67891434, 116.66876762, 104.00698793],
std=[58.395, 57.12, 57.375],
to_rgb=True)
train_pipeline_r50dcnv2 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg_r50dcnv2),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5],
dict(cls='Affine', rotate=[-10, 10]), ['Resize', [0.5, 3.0]]]),
dict(type='EastRandomCrop', target_size=(640, 640)),
dict(type='DBNetTargets', shrink_ratio=0.4),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=['gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'],
visualize=dict(flag=False, boundary_key='gt_shrink')),
dict(
type='Collect',
keys=['img', 'gt_shrink', 'gt_shrink_mask', 'gt_thr', 'gt_thr_mask'])
]
test_pipeline_4068_1024 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=(4068, 1024), # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg_r50dcnv2),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]

View File

@ -1,61 +0,0 @@
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomScaling', size=800, scale=(0.75, 2.5)),
dict(
type='RandomCropFlip', crop_ratio=0.5, iter_num=1, min_area_ratio=0.2),
dict(
type='RandomCropPolyInstances',
instance_key='gt_masks',
crop_ratio=0.8,
min_side_ratio=0.3),
dict(
type='RandomRotate',
rotate_ratio=0.5,
max_angle=60,
pad_with_fixed_color=False,
use_canvas=True),
dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='DRRGTargets'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=[
'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
'gt_cos_map', 'gt_comp_attribs'
],
visualize=dict(flag=False, boundary_key='gt_text_mask')),
dict(
type='Collect',
keys=[
'img', 'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
'gt_top_height_map', 'gt_bot_height_map', 'gt_sin_map',
'gt_cos_map', 'gt_comp_attribs'
])
]
test_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=(1024, 640), # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]

View File

@ -1,120 +0,0 @@
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
# for icdar2015
leval_prop_range_icdar2015 = ((0, 0.4), (0.3, 0.7), (0.6, 1.0))
train_pipeline_icdar2015 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(
type='ColorJitter',
brightness=32.0 / 255,
saturation=0.5,
contrast=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomScaling', size=800, scale=(3. / 4, 5. / 2)),
dict(
type='RandomCropFlip', crop_ratio=0.5, iter_num=1, min_area_ratio=0.2),
dict(
type='RandomCropPolyInstances',
instance_key='gt_masks',
crop_ratio=0.8,
min_side_ratio=0.3),
dict(
type='RandomRotate',
rotate_ratio=0.5,
max_angle=30,
pad_with_fixed_color=False,
use_canvas=True),
dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='Pad', size_divisor=32),
dict(
type='FCENetTargets',
fourier_degree=5,
level_proportion_range=leval_prop_range_icdar2015),
dict(
type='CustomFormatBundle',
keys=['p3_maps', 'p4_maps', 'p5_maps'],
visualize=dict(flag=False, boundary_key=None)),
dict(type='Collect', keys=['img', 'p3_maps', 'p4_maps', 'p5_maps'])
]
img_scale_icdar2015 = (2260, 2260)
test_pipeline_icdar2015 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_icdar2015, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
# for ctw1500
leval_prop_range_ctw1500 = ((0, 0.25), (0.2, 0.65), (0.55, 1.0))
train_pipeline_ctw1500 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(
type='ColorJitter',
brightness=32.0 / 255,
saturation=0.5,
contrast=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(type='RandomScaling', size=800, scale=(3. / 4, 5. / 2)),
dict(
type='RandomCropFlip', crop_ratio=0.5, iter_num=1, min_area_ratio=0.2),
dict(
type='RandomCropPolyInstances',
instance_key='gt_masks',
crop_ratio=0.8,
min_side_ratio=0.3),
dict(
type='RandomRotate',
rotate_ratio=0.5,
max_angle=30,
pad_with_fixed_color=False,
use_canvas=True),
dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='Pad', size_divisor=32),
dict(
type='FCENetTargets',
fourier_degree=5,
level_proportion_range=leval_prop_range_ctw1500),
dict(
type='CustomFormatBundle',
keys=['p3_maps', 'p4_maps', 'p5_maps'],
visualize=dict(flag=False, boundary_key=None)),
dict(type='Collect', keys=['img', 'p3_maps', 'p4_maps', 'p5_maps'])
]
img_scale_ctw1500 = (1080, 736)
test_pipeline_ctw1500 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_ctw1500, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]

View File

@ -1,57 +0,0 @@
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
dict(
type='ScaleAspectJitter',
img_scale=None,
keep_ratio=False,
resize_type='indep_sample_in_range',
scale_range=(640, 2560)),
dict(type='RandomFlip', flip_ratio=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(
type='RandomCropInstances',
target_size=(640, 640),
mask_type='union_all',
instance_key='gt_masks'),
dict(type='Pad', size_divisor=32),
dict(type='DefaultFormatBundle'),
dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
# for ctw1500
img_scale_ctw1500 = (1600, 1600)
test_pipeline_ctw1500 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_ctw1500, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
# for icdar2015
img_scale_icdar2015 = (1920, 1920)
test_pipeline_icdar2015 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_icdar2015, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='RandomFlip'),
dict(type='Normalize', **img_norm_cfg),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]

View File

@ -1,156 +0,0 @@
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
# for ctw1500
img_scale_train_ctw1500 = [(3000, 640)]
shrink_ratio_train_ctw1500 = (1.0, 0.7)
target_size_train_ctw1500 = (640, 640)
train_pipeline_ctw1500 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(
type='ScaleAspectJitter',
img_scale=img_scale_train_ctw1500,
ratio_range=(0.7, 1.3),
aspect_ratio_range=(0.9, 1.1),
multiscale_mode='value',
keep_ratio=False),
# shrink_ratio is from big to small. The 1st must be 1.0
dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_ctw1500),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='RandomRotate', rotate_ratio=1.0, max_angle=10),
dict(
type='RandomCropInstances',
target_size=target_size_train_ctw1500,
instance_key='gt_kernels'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=['gt_kernels', 'gt_mask'],
visualize=dict(flag=False, boundary_key='gt_kernels')),
dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]
img_scale_test_ctw1500 = (3000, 640)
test_pipeline_ctw1500 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_test_ctw1500, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
# for icdar2015
img_scale_train_icdar2015 = [(3000, 736)]
shrink_ratio_train_icdar2015 = (1.0, 0.5)
target_size_train_icdar2015 = (736, 736)
train_pipeline_icdar2015 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(
type='ScaleAspectJitter',
img_scale=img_scale_train_icdar2015,
ratio_range=(0.7, 1.3),
aspect_ratio_range=(0.9, 1.1),
multiscale_mode='value',
keep_ratio=False),
dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_icdar2015),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='RandomRotate', rotate_ratio=1.0, max_angle=10),
dict(
type='RandomCropInstances',
target_size=target_size_train_icdar2015,
instance_key='gt_kernels'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=['gt_kernels', 'gt_mask'],
visualize=dict(flag=False, boundary_key='gt_kernels')),
dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]
img_scale_test_icdar2015 = (1333, 736)
test_pipeline_icdar2015 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_test_icdar2015, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
# for icdar2017
img_scale_train_icdar2017 = [(3000, 800)]
shrink_ratio_train_icdar2017 = (1.0, 0.5)
target_size_train_icdar2017 = (800, 800)
train_pipeline_icdar2017 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(
type='ScaleAspectJitter',
img_scale=img_scale_train_icdar2017,
ratio_range=(0.7, 1.3),
aspect_ratio_range=(0.9, 1.1),
multiscale_mode='value',
keep_ratio=False),
dict(type='PANetTargets', shrink_ratio=shrink_ratio_train_icdar2017),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='RandomRotate', rotate_ratio=1.0, max_angle=10),
dict(
type='RandomCropInstances',
target_size=target_size_train_icdar2017,
instance_key='gt_kernels'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=['gt_kernels', 'gt_mask'],
visualize=dict(flag=False, boundary_key='gt_kernels')),
dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]
img_scale_test_icdar2017 = (1333, 800)
test_pipeline_icdar2017 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_test_icdar2017, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]

View File

@ -1,70 +0,0 @@
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(
type='ScaleAspectJitter',
img_scale=[(3000, 736)],
ratio_range=(0.5, 3),
aspect_ratio_range=(1, 1),
multiscale_mode='value',
long_size_bound=1280,
short_size_bound=640,
resize_type='long_short_bound',
keep_ratio=False),
dict(type='PSENetTargets'),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='RandomRotate', rotate_ratio=1.0, max_angle=10),
dict(
type='RandomCropInstances',
target_size=(640, 640),
instance_key='gt_kernels'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=['gt_kernels', 'gt_mask'],
visualize=dict(flag=False, boundary_key='gt_kernels')),
dict(type='Collect', keys=['img', 'gt_kernels', 'gt_mask'])
]
# for ctw1500
img_scale_test_ctw1500 = (1280, 1280)
test_pipeline_ctw1500 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_test_ctw1500, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]
# for icdar2015
img_scale_test_icdar2015 = (2240, 2240)
test_pipeline_icdar2015 = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=img_scale_test_icdar2015, # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]

View File

@ -1,66 +0,0 @@
img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='LoadTextAnnotations',
with_bbox=True,
with_mask=True,
poly2mask=False),
dict(type='ColorJitter', brightness=32.0 / 255, saturation=0.5),
dict(type='Normalize', **img_norm_cfg),
dict(
type='RandomCropPolyInstances',
instance_key='gt_masks',
crop_ratio=0.65,
min_side_ratio=0.3),
dict(
type='RandomRotate',
rotate_ratio=0.5,
max_angle=20,
pad_with_fixed_color=False,
use_canvas=True),
dict(
type='ScaleAspectJitter',
img_scale=[(3000, 736)], # unused
ratio_range=(0.7, 1.3),
aspect_ratio_range=(0.9, 1.1),
multiscale_mode='value',
long_size_bound=800,
short_size_bound=480,
resize_type='long_short_bound',
keep_ratio=False),
dict(type='SquareResizePad', target_size=800, pad_ratio=0.6),
dict(type='RandomFlip', flip_ratio=0.5, direction='horizontal'),
dict(type='TextSnakeTargets'),
dict(type='Pad', size_divisor=32),
dict(
type='CustomFormatBundle',
keys=[
'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
'gt_radius_map', 'gt_sin_map', 'gt_cos_map'
],
visualize=dict(flag=False, boundary_key='gt_text_mask')),
dict(
type='Collect',
keys=[
'img', 'gt_text_mask', 'gt_center_region_mask', 'gt_mask',
'gt_radius_map', 'gt_sin_map', 'gt_cos_map'
])
]
test_pipeline = [
dict(type='LoadImageFromFile', color_type='color_ignore_orientation'),
dict(
type='MultiScaleFlipAug',
img_scale=(1333, 736), # used by Resize
flip=False,
transforms=[
dict(type='Resize', keep_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='Pad', size_divisor=32),
dict(type='ImageToTensor', keys=['img']),
dict(type='Collect', keys=['img']),
])
]

View File

@ -1,35 +0,0 @@
img_norm_cfg = dict(mean=[127], std=[127])
train_pipeline = [
dict(type='LoadImageFromFile', color_type='grayscale'),
dict(
type='ResizeOCR',
height=32,
min_width=100,
max_width=100,
keep_aspect_ratio=False),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img'],
meta_keys=['filename', 'resize_shape', 'text', 'valid_ratio']),
]
test_pipeline = [
dict(type='LoadImageFromFile', color_type='grayscale'),
dict(
type='ResizeOCR',
height=32,
min_width=32,
max_width=None,
keep_aspect_ratio=True),
dict(type='Normalize', **img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'resize_shape', 'valid_ratio', 'img_norm_cfg',
'ori_filename', 'img_shape', 'ori_shape'
]),
]

View File

@ -1,37 +0,0 @@
img_norm_cfg = dict(mean=[0.5], std=[0.5])
train_pipeline = [
dict(type='LoadImageFromFile', color_type='grayscale'),
dict(
type='ResizeOCR',
height=32,
min_width=100,
max_width=100,
keep_aspect_ratio=False),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio'
]),
]
test_pipeline = [
dict(type='LoadImageFromFile', color_type='grayscale'),
dict(
type='ResizeOCR',
height=32,
min_width=32,
max_width=100,
keep_aspect_ratio=False),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'resize_shape', 'valid_ratio',
'img_norm_cfg', 'ori_filename', 'img_shape'
]),
]

View File

@ -1,42 +0,0 @@
img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='ResizeOCR',
height=48,
min_width=48,
max_width=160,
keep_aspect_ratio=True),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'img_shape', 'text', 'valid_ratio',
'resize_shape'
]),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiRotateAugOCR',
rotate_degrees=[0, 90, 270],
transforms=[
dict(
type='ResizeOCR',
height=48,
min_width=48,
max_width=160,
keep_aspect_ratio=True),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'img_shape', 'valid_ratio',
'img_norm_cfg', 'ori_filename', 'resize_shape'
]),
])
]

View File

@ -1,38 +0,0 @@
img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='ResizeOCR',
height=32,
min_width=32,
max_width=160,
keep_aspect_ratio=True,
width_downsample_ratio=0.25),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio'
]),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='ResizeOCR',
height=32,
min_width=32,
max_width=160,
keep_aspect_ratio=True),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'resize_shape', 'valid_ratio',
'img_norm_cfg', 'ori_filename', 'img_shape'
])
]

View File

@ -1,43 +0,0 @@
img_norm_cfg = dict(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='ResizeOCR',
height=48,
min_width=48,
max_width=160,
keep_aspect_ratio=True,
width_downsample_ratio=0.25),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'resize_shape', 'text', 'valid_ratio'
]),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiRotateAugOCR',
rotate_degrees=[0, 90, 270],
transforms=[
dict(
type='ResizeOCR',
height=48,
min_width=48,
max_width=160,
keep_aspect_ratio=True,
width_downsample_ratio=0.25),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'resize_shape', 'valid_ratio',
'img_norm_cfg', 'ori_filename', 'img_shape'
]),
])
]

View File

@ -1,44 +0,0 @@
img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='ResizeOCR',
height=32,
min_width=100,
max_width=100,
keep_aspect_ratio=False,
width_downsample_ratio=0.25),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'img_shape', 'text', 'valid_ratio',
'resize_shape'
]),
]
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='MultiRotateAugOCR',
rotate_degrees=[0, 90, 270],
transforms=[
dict(
type='ResizeOCR',
height=32,
min_width=100,
max_width=100,
keep_aspect_ratio=False,
width_downsample_ratio=0.25),
dict(type='ToTensorOCR'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'ori_shape', 'img_shape', 'valid_ratio',
'resize_shape', 'img_norm_cfg', 'ori_filename'
]),
])
]

View File

@ -1,66 +0,0 @@
img_norm_cfg = dict(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
gt_label_convertor = dict(
type='SegConvertor', dict_type='DICT36', with_unknown=True, lower=True)
train_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='RandomPaddingOCR',
max_ratio=[0.15, 0.2, 0.15, 0.2],
box_type='char_quads'),
dict(type='OpencvToPil'),
dict(
type='RandomRotateImageBox',
min_angle=-17,
max_angle=17,
box_type='char_quads'),
dict(type='PilToOpencv'),
dict(
type='ResizeOCR',
height=64,
min_width=64,
max_width=512,
keep_aspect_ratio=True),
dict(
type='OCRSegTargets',
label_convertor=gt_label_convertor,
box_type='char_quads'),
dict(type='RandomRotate', rotate_ratio=0.5, max_angle=15),
dict(type='ColorJitter', brightness=0.4, contrast=0.4, saturation=0.4),
dict(type='ToTensorOCR'),
dict(type='FancyPCA'),
dict(type='NormalizeOCR', **img_norm_cfg),
dict(
type='CustomFormatBundle',
keys=['gt_kernels'],
visualize=dict(flag=False, boundary_key=None),
call_super=False),
dict(
type='Collect',
keys=['img', 'gt_kernels'],
meta_keys=['filename', 'ori_shape', 'resize_shape'])
]
test_img_norm_cfg = dict(
mean=[x * 255 for x in img_norm_cfg['mean']],
std=[x * 255 for x in img_norm_cfg['std']])
test_pipeline = [
dict(type='LoadImageFromFile'),
dict(
type='ResizeOCR',
height=64,
min_width=64,
max_width=None,
keep_aspect_ratio=True),
dict(type='Normalize', **test_img_norm_cfg),
dict(type='DefaultFormatBundle'),
dict(
type='Collect',
keys=['img'],
meta_keys=[
'filename', 'resize_shape', 'img_norm_cfg', 'ori_filename',
'img_shape', 'ori_shape'
])
]