File size: 5,918 Bytes
e8f2571 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 |
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
# Example to use different file client
# Method 1: simply set the data root and let the file I/O module
# automatically infer from prefix (not support LMDB and Memcache yet)
# data_root = 's3://openmmlab/datasets/detection/coco/'
# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
# backend_args = dict(
# backend='petrel',
# path_mapping=dict({
# './data/': 's3://openmmlab/datasets/detection/',
# 'data/': 's3://openmmlab/datasets/detection/'
# }))
backend_args = None
color_space = [
[dict(type='ColorTransform')],
[dict(type='AutoContrast')],
[dict(type='Equalize')],
[dict(type='Sharpness')],
[dict(type='Posterize')],
[dict(type='Solarize')],
[dict(type='Color')],
[dict(type='Contrast')],
[dict(type='Brightness')],
]
geometric = [
[dict(type='Rotate')],
[dict(type='ShearX')],
[dict(type='ShearY')],
[dict(type='TranslateX')],
[dict(type='TranslateY')],
]
scale = [(1333, 400), (1333, 1200)]
branch_field = ['sup', 'unsup_teacher', 'unsup_student']
# pipeline used to augment labeled data,
# which will be sent to student model for supervised training.
sup_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='RandomResize', scale=scale, keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='RandAugment', aug_space=color_space, aug_num=1),
dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
dict(
type='MultiBranch',
branch_field=branch_field,
sup=dict(type='PackDetInputs'))
]
# pipeline used to augment unlabeled data weakly,
# which will be sent to teacher model for predicting pseudo instances.
weak_pipeline = [
dict(type='RandomResize', scale=scale, keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'flip', 'flip_direction',
'homography_matrix')),
]
# pipeline used to augment unlabeled data strongly,
# which will be sent to student model for unsupervised training.
strong_pipeline = [
dict(type='RandomResize', scale=scale, keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(
type='RandomOrder',
transforms=[
dict(type='RandAugment', aug_space=color_space, aug_num=1),
dict(type='RandAugment', aug_space=geometric, aug_num=1),
]),
dict(type='RandomErasing', n_patches=(1, 5), ratio=(0, 0.2)),
dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'flip', 'flip_direction',
'homography_matrix')),
]
# pipeline used to augment unlabeled data into different views
unsup_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadEmptyAnnotations'),
dict(
type='MultiBranch',
branch_field=branch_field,
unsup_teacher=weak_pipeline,
unsup_student=strong_pipeline,
)
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
batch_size = 5
num_workers = 5
# There are two common semi-supervised learning settings on the coco dataset：
# (1) Divide the train2017 into labeled and unlabeled datasets
# by a fixed percentage, such as 1%, 2%, 5% and 10%.
# The format of labeled_ann_file and unlabeled_ann_file are
# instances_train2017.{fold}@{percent}.json, and
# instances_train2017.{fold}@{percent}-unlabeled.json
# `fold` is used for cross-validation, and `percent` represents
# the proportion of labeled data in the train2017.
# (2) Choose the train2017 as the labeled dataset
# and unlabeled2017 as the unlabeled dataset.
# The labeled_ann_file and unlabeled_ann_file are
# instances_train2017.json and image_info_unlabeled2017.json
# We use this configuration by default.
labeled_dataset = dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/instances_train2017.json',
data_prefix=dict(img='train2017/'),
filter_cfg=dict(filter_empty_gt=True, min_size=32),
pipeline=sup_pipeline,
backend_args=backend_args)
unlabeled_dataset = dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/instances_unlabeled2017.json',
data_prefix=dict(img='unlabeled2017/'),
filter_cfg=dict(filter_empty_gt=False),
pipeline=unsup_pipeline,
backend_args=backend_args)
train_dataloader = dict(
batch_size=batch_size,
num_workers=num_workers,
persistent_workers=True,
sampler=dict(
type='GroupMultiSourceSampler',
batch_size=batch_size,
source_ratio=[1, 4]),
dataset=dict(
type='ConcatDataset', datasets=[labeled_dataset, unlabeled_dataset]))
val_dataloader = dict(
batch_size=1,
num_workers=2,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/instances_val2017.json',
data_prefix=dict(img='val2017/'),
test_mode=True,
pipeline=test_pipeline,
backend_args=backend_args))
test_dataloader = val_dataloader
val_evaluator = dict(
type='CocoMetric',
ann_file=data_root + 'annotations/instances_val2017.json',
metric='bbox',
format_only=False,
backend_args=backend_args)
test_evaluator = val_evaluator
|