Spaces:
Build error
Build error
File size: 5,787 Bytes
6ad06e7 254a9f5 6ad06e7 254a9f5 6ad06e7 49aa0b6 6ad06e7 254a9f5 6ad06e7 49aa0b6 6ad06e7 |
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 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 |
file_client_args = dict(backend='disk')
model = dict(
type='PSENet',
backbone=dict(
type='mmdet.ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=-1,
norm_cfg=dict(type='SyncBN', requires_grad=True),
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
norm_eval=True,
style='caffe'),
neck=dict(
type='FPNF',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
fusion_type='concat'),
det_head=dict(
type='PSEHead',
in_channels=[256],
hidden_dim=256,
out_channel=7,
module_loss=dict(type='PSEModuleLoss'),
postprocessor=dict(type='PSEPostprocessor', text_repr_type='poly')),
data_preprocessor=dict(
type='TextDetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=32))
default_scope = 'mmocr'
env_cfg = dict(
cudnn_benchmark=True,
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
dist_cfg=dict(backend='nccl'))
randomness = dict(seed=None)
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=100),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', interval=5),
sampler_seed=dict(type='DistSamplerSeedHook'),
sync_buffer=dict(type='SyncBuffersHook'),
visualization=dict(
type='VisualizationHook',
interval=1,
enable=False,
show=False,
draw_gt=False,
draw_pred=False))
log_level = 'INFO'
log_processor = dict(type='LogProcessor', window_size=100, by_epoch=True)
load_from = None
resume = True
val_evaluator = dict(type='HmeanIOUMetric')
test_evaluator = dict(type='HmeanIOUMetric')
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
type='TextDetLocalVisualizer',
name='visualizer',
vis_backends=[dict(type='LocalVisBackend')])
max_epochs = 50
optim_wrapper = dict(
type='OptimWrapper', optimizer=dict(type='Adam', lr=0.001))
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=50, val_interval=20)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [dict(type='PolyLR', power=0.9, end=50)]
train_dataloader = dict(
batch_size=10,
num_workers=16,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type='OCRDataset',
data_root='data/det/vl+vc-textdet',
ann_file='textdet_train.json',
data_prefix=dict(img_path='imgs/'),
filter_cfg=dict(filter_empty_gt=True, min_size=32),
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='disk'),
color_type='color_ignore_orientation'),
dict(
type='LoadOCRAnnotations',
with_polygon=True,
with_bbox=True,
with_label=True),
dict(
type='TorchVisionWrapper',
op='ColorJitter',
brightness=0.12549019607843137,
saturation=0.5),
dict(type='FixInvalidPolygon'),
dict(
type='ShortScaleAspectJitter',
short_size=736,
scale_divisor=32),
dict(type='RandomRotate', max_angle=10),
dict(type='TextDetRandomCrop', target_size=(736, 736)),
dict(type='Pad', size=(736, 736)),
dict(
type='PackTextDetInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]))
val_dataloader = dict(
batch_size=4,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='OCRDataset',
data_root='data/det/textdet-thvote',
ann_file='textdet_test.json',
data_prefix=dict(img_path='imgs/'),
test_mode=True,
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='disk'),
color_type='color_ignore_orientation'),
dict(type='Resize', scale=(2240, 2240), keep_ratio=True),
dict(
type='LoadOCRAnnotations',
with_polygon=True,
with_bbox=True,
with_label=True),
dict(
type='PackTextDetInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]))
test_dataloader = dict(
batch_size=4,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='OCRDataset',
data_root='data/det/textdet-thvote',
ann_file='textdet_test.json',
data_prefix=dict(img_path='imgs/'),
test_mode=True,
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='disk'),
color_type='color_ignore_orientation'),
dict(type='Resize', scale=(2240, 2240), keep_ratio=True),
dict(
type='LoadOCRAnnotations',
with_polygon=True,
with_bbox=True,
with_label=True),
dict(
type='PackTextDetInputs',
meta_keys=('img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]))
auto_scale_lr = dict(base_batch_size=32)
launcher = 'none'
work_dir = './work_dirs/psenet_resnet50_fpnf_votecount'
|