mmocr1.x中模型训练totaltext数据集结果为0

[w1125]

使用Oclip-dbnetpp模型训练数据集totaltext，最终的输出结果为0，迁移dbnet18中的关于totaltext的配置
2023/04/16 16:12:05 - mmengine - INFO - Config:
model = dict(
type='DBNet',
backbone=dict(
type='CLIPResNet',
init_cfg=dict(
type='Pretrained',
checkpoint=
'https://download.openmmlab.com/mmocr/backbone/resnet50-oclip-7ba0c533.pth'
)),
neck=dict(
type='FPNC',
in_channels=[256, 512, 1024, 2048],
lateral_channels=256,
asf_cfg=dict(attention_type='ScaleChannelSpatial')),
det_head=dict(
type='DBHead',
in_channels=256,
module_loss=dict(type='DBModuleLoss'),
postprocessor=dict(
type='DBPostprocessor', text_repr_type='quad',
epsilon_ratio=0.002)),
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))
train_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='FixInvalidPolygon', min_poly_points=4),
dict(
type='TorchVisionWrapper',
op='ColorJitter',
brightness=0.12549019607843137,
saturation=0.5),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5], {
'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',
file_client_args=dict(backend='disk'),
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'))
]
totaltext_textdet_data_root = 'data/totaltext'
totaltext_textdet_train = dict(
type='OCRDataset',
data_root='data/totaltext',
ann_file='textdet_train.json',
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='FixInvalidPolygon', min_poly_points=4),
dict(
type='TorchVisionWrapper',
op='ColorJitter',
brightness=0.12549019607843137,
saturation=0.5),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5], {
'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'))
])
totaltext_textdet_test = dict(
type='OCRDataset',
data_root='data/totaltext',
ann_file='textdet_test.json',
test_mode=True,
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='disk'),
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'))
])
default_scope = 'mmocr'
env_cfg = dict(
cudnn_benchmark=False,
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=5),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', interval=20),
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=10, by_epoch=True)
load_from = None
resume = False
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')])
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='SGD', lr=0.002, momentum=0.9, weight_decay=0.0001))
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=1200, val_interval=20)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
param_scheduler = [
dict(type='LinearLR', end=200, start_factor=0.001),
dict(type='PolyLR', power=0.9, eta_min=1e-07, begin=200, end=1200)
]
file_client_args = dict(backend='disk')
train_dataloader = dict(
batch_size=8,
num_workers=24,
pin_memory=True,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type='OCRDataset',
data_root='data/totaltext',
ann_file='textdet_train.json',
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='FixInvalidPolygon', min_poly_points=4),
dict(
type='TorchVisionWrapper',
op='ColorJitter',
brightness=0.12549019607843137,
saturation=0.5),
dict(
type='ImgAugWrapper',
args=[['Fliplr', 0.5], {
'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'))
]))
val_dataloader = dict(
batch_size=1,
num_workers=1,
pin_memory=True,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='OCRDataset',
data_root='data/totaltext',
ann_file='textdet_test.json',
test_mode=True,
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='disk'),
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'))
]))
test_dataloader = dict(
batch_size=1,
num_workers=1,
pin_memory=True,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type='OCRDataset',
data_root='data/totaltext',
ann_file='textdet_test.json',
test_mode=True,
pipeline=[
dict(
type='LoadImageFromFile',
file_client_args=dict(backend='disk'),
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'))
]))
auto_scale_lr = dict(base_batch_size=16)
launcher = 'none'
work_dir = 'result/PANet'
输出：precision: 0.0000 icdar/recall: 0.0000 icdar/hmean: 0.0000 data_time: 0.0383 time: 0.0643