Skip to content

GitLab

Commit a8562a56 authored by luopl's avatar luopl
Browse files

Initial commit

parents
Pipeline #1564 canceled with stages
Hide whitespace changes
Inline Side-by-side
Showing with 1952 additions and 0 deletions
configs/_base_/datasets/objects365v2_detection.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'Objects365V2Dataset'
data_root = 'data/Objects365/Obj365_v2/'
# 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
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
# If you don't have a gt annotation, delete the pipeline
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
batch_sampler=dict(type='AspectRatioBatchSampler'),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/zhiyuan_objv2_train.json',
data_prefix=dict(img='train/'),
filter_cfg=dict(filter_empty_gt=True, min_size=32),
pipeline=train_pipeline,
backend_args=backend_args))
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/zhiyuan_objv2_val.json',
data_prefix=dict(img='val/'),
test_mode=True,
pipeline=test_pipeline,
backend_args=backend_args))
test_dataloader = val_dataloader
val_evaluator = dict(
type='CocoMetric',
ann_file=data_root + 'annotations/zhiyuan_objv2_val.json',
metric='bbox',
format_only=False,
backend_args=backend_args)
test_evaluator = val_evaluator
configs/_base_/datasets/openimages_detection.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'OpenImagesDataset'
data_root = 'data/OpenImages/'
# 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
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', scale=(1024, 800), keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1024, 800), keep_ratio=True),
# avoid bboxes being resized
dict(type='LoadAnnotations', with_bbox=True),
# TODO: find a better way to collect image_level_labels
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'instances', 'image_level_labels'))
]
train_dataloader = dict(
batch_size=2,
num_workers=0, # workers_per_gpu > 0 may occur out of memory
persistent_workers=False,
sampler=dict(type='DefaultSampler', shuffle=True),
batch_sampler=dict(type='AspectRatioBatchSampler'),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/oidv6-train-annotations-bbox.csv',
data_prefix=dict(img='OpenImages/train/'),
label_file='annotations/class-descriptions-boxable.csv',
hierarchy_file='annotations/bbox_labels_600_hierarchy.json',
meta_file='annotations/train-image-metas.pkl',
pipeline=train_pipeline,
backend_args=backend_args))
val_dataloader = dict(
batch_size=1,
num_workers=0,
persistent_workers=False,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/validation-annotations-bbox.csv',
data_prefix=dict(img='OpenImages/validation/'),
label_file='annotations/class-descriptions-boxable.csv',
hierarchy_file='annotations/bbox_labels_600_hierarchy.json',
meta_file='annotations/validation-image-metas.pkl',
image_level_ann_file='annotations/validation-'
'annotations-human-imagelabels-boxable.csv',
pipeline=test_pipeline,
backend_args=backend_args))
test_dataloader = val_dataloader
val_evaluator = dict(
type='OpenImagesMetric',
iou_thrs=0.5,
ioa_thrs=0.5,
use_group_of=True,
get_supercategory=True)
test_evaluator = val_evaluator
configs/_base_/datasets/refcoco+.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'RefCocoDataset'
data_root = 'data/coco/'
backend_args = None
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(
type='LoadAnnotations',
with_mask=True,
with_bbox=False,
with_seg=False,
with_label=False),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'gt_masks', 'text'))
]
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,
data_prefix=dict(img_path='train2014/'),
ann_file='refcoco+/instances.json',
split_file='refcoco+/refs(unc).p',
split='val',
text_mode='select_first',
pipeline=test_pipeline))
test_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,
data_prefix=dict(img_path='train2014/'),
ann_file='refcoco+/instances.json',
split_file='refcoco+/refs(unc).p',
split='testA', # or 'testB'
text_mode='select_first',
pipeline=test_pipeline))
val_evaluator = dict(type='RefSegMetric', metric=['cIoU', 'mIoU'])
test_evaluator = val_evaluator
configs/_base_/datasets/refcoco.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'RefCocoDataset'
data_root = 'data/coco/'
backend_args = None
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(
type='LoadAnnotations',
with_mask=True,
with_bbox=False,
with_seg=False,
with_label=False),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'gt_masks', 'text'))
]
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,
data_prefix=dict(img_path='train2014/'),
ann_file='refcoco/instances.json',
split_file='refcoco/refs(unc).p',
split='val',
text_mode='select_first',
pipeline=test_pipeline))
test_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,
data_prefix=dict(img_path='train2014/'),
ann_file='refcoco/instances.json',
split_file='refcoco/refs(unc).p',
split='testA', # or 'testB'
text_mode='select_first',
pipeline=test_pipeline))
val_evaluator = dict(type='RefSegMetric', metric=['cIoU', 'mIoU'])
test_evaluator = val_evaluator
configs/_base_/datasets/refcocog.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'RefCocoDataset'
data_root = 'data/coco/'
backend_args = None
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
dict(
type='LoadAnnotations',
with_mask=True,
with_bbox=False,
with_seg=False,
with_label=False),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor', 'gt_masks', 'text'))
]
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,
data_prefix=dict(img_path='train2014/'),
ann_file='refcocog/instances.json',
split_file='refcocog/refs(umd).p',
split='val',
text_mode='select_first',
pipeline=test_pipeline))
test_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,
data_prefix=dict(img_path='train2014/'),
ann_file='refcocog/instances.json',
split_file='refcocog/refs(umd).p',
split='test',
text_mode='select_first',
pipeline=test_pipeline))
val_evaluator = dict(type='RefSegMetric', metric=['cIoU', 'mIoU'])
test_evaluator = val_evaluator
configs/_base_/datasets/semi_coco_detection.py 0 → 100644
View file @ a8562a56
# 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
configs/_base_/datasets/v3det.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'V3DetDataset'
data_root = 'data/V3Det/'
backend_args = None
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='RandomChoiceResize',
scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
(1333, 768), (1333, 800)],
keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1333, 800), keep_ratio=True),
# If you don't have a gt annotation, delete the pipeline
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
batch_sampler=dict(type='AspectRatioBatchSampler'),
dataset=dict(
type='ClassBalancedDataset',
oversample_thr=1e-3,
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='annotations/v3det_2023_v1_train.json',
data_prefix=dict(img=''),
filter_cfg=dict(filter_empty_gt=True, min_size=4),
pipeline=train_pipeline,
backend_args=backend_args)))
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/v3det_2023_v1_val.json',
data_prefix=dict(img=''),
test_mode=True,
pipeline=test_pipeline,
backend_args=backend_args))
test_dataloader = val_dataloader
val_evaluator = dict(
type='CocoMetric',
ann_file=data_root + 'annotations/v3det_2023_v1_val.json',
metric='bbox',
format_only=False,
backend_args=backend_args,
use_mp_eval=True,
proposal_nums=[300])
test_evaluator = val_evaluator
configs/_base_/datasets/voc0712.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'VOCDataset'
data_root = 'data/VOCdevkit/'
# 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/segmentation/VOCdevkit/'
# 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/segmentation/',
# 'data/': 's3://openmmlab/datasets/segmentation/'
# }))
backend_args = None
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', scale=(1000, 600), keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(1000, 600), keep_ratio=True),
# avoid bboxes being resized
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
batch_sampler=dict(type='AspectRatioBatchSampler'),
dataset=dict(
type='RepeatDataset',
times=3,
dataset=dict(
type='ConcatDataset',
# VOCDataset will add different `dataset_type` in dataset.metainfo,
# which will get error if using ConcatDataset. Adding
# `ignore_keys` can avoid this error.
ignore_keys=['dataset_type'],
datasets=[
dict(
type=dataset_type,
data_root=data_root,
ann_file='VOC2007/ImageSets/Main/trainval.txt',
data_prefix=dict(sub_data_root='VOC2007/'),
filter_cfg=dict(
filter_empty_gt=True, min_size=32, bbox_min_size=32),
pipeline=train_pipeline,
backend_args=backend_args),
dict(
type=dataset_type,
data_root=data_root,
ann_file='VOC2012/ImageSets/Main/trainval.txt',
data_prefix=dict(sub_data_root='VOC2012/'),
filter_cfg=dict(
filter_empty_gt=True, min_size=32, bbox_min_size=32),
pipeline=train_pipeline,
backend_args=backend_args)
])))
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='VOC2007/ImageSets/Main/test.txt',
data_prefix=dict(sub_data_root='VOC2007/'),
test_mode=True,
pipeline=test_pipeline,
backend_args=backend_args))
test_dataloader = val_dataloader
# Pascal VOC2007 uses `11points` as default evaluate mode, while PASCAL
# VOC2012 defaults to use 'area'.
val_evaluator = dict(type='VOCMetric', metric='mAP', eval_mode='11points')
test_evaluator = val_evaluator
configs/_base_/datasets/wider_face.py 0 → 100644
View file @ a8562a56
# dataset settings
dataset_type = 'WIDERFaceDataset'
data_root = 'data/WIDERFace/'
# 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/cityscapes/'
# 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
img_scale = (640, 640) # VGA resolution
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(type='Resize', scale=img_scale, keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=img_scale, keep_ratio=True),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=True),
batch_sampler=dict(type='AspectRatioBatchSampler'),
dataset=dict(
type=dataset_type,
data_root=data_root,
ann_file='train.txt',
data_prefix=dict(img='WIDER_train'),
filter_cfg=dict(filter_empty_gt=True, bbox_min_size=17, min_size=32),
pipeline=train_pipeline))
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='val.txt',
data_prefix=dict(img='WIDER_val'),
test_mode=True,
pipeline=test_pipeline))
test_dataloader = val_dataloader
val_evaluator = dict(
# TODO: support WiderFace-Evaluation for easy, medium, hard cases
type='VOCMetric',
metric='mAP',
eval_mode='11points')
test_evaluator = val_evaluator
configs/_base_/datasets/youtube_vis.py 0 → 100644
View file @ a8562a56
dataset_type = 'YouTubeVISDataset'
data_root = 'data/youtube_vis_2019/'
dataset_version = data_root[-5:-1] # 2019 or 2021
backend_args = None
# dataset settings
train_pipeline = [
dict(
type='UniformRefFrameSample',
num_ref_imgs=1,
frame_range=100,
filter_key_img=True),
dict(
type='TransformBroadcaster',
share_random_params=True,
transforms=[
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadTrackAnnotations', with_mask=True),
dict(type='Resize', scale=(640, 360), keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
]),
dict(type='PackTrackInputs')
]
test_pipeline = [
dict(
type='TransformBroadcaster',
transforms=[
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='Resize', scale=(640, 360), keep_ratio=True),
dict(type='LoadTrackAnnotations', with_mask=True),
]),
dict(type='PackTrackInputs')
]
# dataloader
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
# sampler=dict(type='TrackImgSampler'), # image-based sampling
sampler=dict(type='DefaultSampler', shuffle=True),
batch_sampler=dict(type='TrackAspectRatioBatchSampler'),
dataset=dict(
type=dataset_type,
data_root=data_root,
dataset_version=dataset_version,
ann_file='annotations/youtube_vis_2019_train.json',
data_prefix=dict(img_path='train/JPEGImages'),
pipeline=train_pipeline))
val_dataloader = dict(
batch_size=1,
num_workers=2,
persistent_workers=True,
drop_last=False,
sampler=dict(type='DefaultSampler', shuffle=False, round_up=False),
dataset=dict(
type=dataset_type,
data_root=data_root,
dataset_version=dataset_version,
ann_file='annotations/youtube_vis_2019_valid.json',
data_prefix=dict(img_path='valid/JPEGImages'),
test_mode=True,
pipeline=test_pipeline))
test_dataloader = val_dataloader
configs/_base_/default_runtime.py 0 → 100644
View file @ a8562a56
default_scope = 'mmdet'
default_hooks = dict(
timer=dict(type='IterTimerHook'),
logger=dict(type='LoggerHook', interval=50),
param_scheduler=dict(type='ParamSchedulerHook'),
checkpoint=dict(type='CheckpointHook', interval=1),
sampler_seed=dict(type='DistSamplerSeedHook'),
visualization=dict(type='DetVisualizationHook'))
env_cfg = dict(
cudnn_benchmark=False,
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
dist_cfg=dict(backend='nccl'),
)
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
log_level = 'INFO'
load_from = None
resume = False
configs/_base_/models/cascade-mask-rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# model settings
model = dict(
type='CascadeRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_mask=True,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
roi_head=dict(
type='CascadeRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
],
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=80,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False)
]),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
configs/_base_/models/cascade-rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# model settings
model = dict(
type='CascadeRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
roi_head=dict(
type='CascadeRoIHead',
num_stages=3,
stage_loss_weights=[1, 0.5, 0.25],
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 0.1]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
loss_weight=1.0)),
dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067]),
reg_class_agnostic=True,
loss_cls=dict(
type='CrossEntropyLoss',
use_sigmoid=False,
loss_weight=1.0),
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
]),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=[
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)
]),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
configs/_base_/models/fast-rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# model settings
model = dict(
type='FastRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
configs/_base_/models/faster-rcnn_r50-caffe-c4.py 0 → 100644
View file @ a8562a56
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='FasterRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[103.530, 116.280, 123.675],
std=[1.0, 1.0, 1.0],
bgr_to_rgb=False,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=3,
strides=(1, 2, 2),
dilations=(1, 1, 1),
out_indices=(2, ),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
rpn_head=dict(
type='RPNHead',
in_channels=1024,
feat_channels=1024,
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4, 8, 16, 32],
ratios=[0.5, 1.0, 2.0],
strides=[16]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
shared_head=dict(
type='ResLayer',
depth=50,
stage=3,
stride=2,
dilation=1,
style='caffe',
norm_cfg=norm_cfg,
norm_eval=True,
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=1024,
featmap_strides=[16]),
bbox_head=dict(
type='BBoxHead',
with_avg_pool=True,
roi_feat_size=7,
in_channels=2048,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=12000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=6000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
configs/_base_/models/faster-rcnn_r50-caffe-dc5.py 0 → 100644
View file @ a8562a56
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='FasterRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[103.530, 116.280, 123.675],
std=[1.0, 1.0, 1.0],
bgr_to_rgb=False,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
strides=(1, 2, 2, 1),
dilations=(1, 1, 1, 2),
out_indices=(3, ),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
rpn_head=dict(
type='RPNHead',
in_channels=2048,
feat_channels=2048,
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4, 8, 16, 32],
ratios=[0.5, 1.0, 2.0],
strides=[16]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=2048,
featmap_strides=[16]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=2048,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=12000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms=dict(type='nms', iou_threshold=0.7),
nms_pre=6000,
max_per_img=1000,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)))
configs/_base_/models/faster-rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# model settings
model = dict(
type='FasterRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100)
# soft-nms is also supported for rcnn testing
# e.g., nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.05)
))
configs/_base_/models/mask-rcnn_r50-caffe-c4.py 0 → 100644
View file @ a8562a56
# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
type='MaskRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[103.530, 116.280, 123.675],
std=[1.0, 1.0, 1.0],
bgr_to_rgb=False,
pad_mask=True,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=3,
strides=(1, 2, 2),
dilations=(1, 1, 1),
out_indices=(2, ),
frozen_stages=1,
norm_cfg=norm_cfg,
norm_eval=True,
style='caffe',
init_cfg=dict(
type='Pretrained',
checkpoint='open-mmlab://detectron2/resnet50_caffe')),
rpn_head=dict(
type='RPNHead',
in_channels=1024,
feat_channels=1024,
anchor_generator=dict(
type='AnchorGenerator',
scales=[2, 4, 8, 16, 32],
ratios=[0.5, 1.0, 2.0],
strides=[16]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
shared_head=dict(
type='ResLayer',
depth=50,
stage=3,
stride=2,
dilation=1,
style='caffe',
norm_cfg=norm_cfg,
norm_eval=True),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=1024,
featmap_strides=[16]),
bbox_head=dict(
type='BBoxHead',
with_avg_pool=True,
roi_feat_size=7,
in_channels=2048,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
mask_roi_extractor=None,
mask_head=dict(
type='FCNMaskHead',
num_convs=0,
in_channels=2048,
conv_out_channels=256,
num_classes=80,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=0,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=12000,
max_per_img=2000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=False,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=14,
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=6000,
nms=dict(type='nms', iou_threshold=0.7),
max_per_img=1000,
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
configs/_base_/models/mask-rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# model settings
model = dict(
type='MaskRCNN',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_mask=True,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
scales=[8],
ratios=[0.5, 1.0, 2.0],
strides=[4, 8, 16, 32, 64]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
roi_head=dict(
type='StandardRoIHead',
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=dict(
type='Shared2FCBBoxHead',
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=80,
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2]),
reg_class_agnostic=False,
loss_cls=dict(
type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
mask_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
mask_head=dict(
type='FCNMaskHead',
num_convs=4,
in_channels=256,
conv_out_channels=256,
num_classes=80,
loss_mask=dict(
type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
# model training and testing settings
train_cfg=dict(
rpn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.3,
min_pos_iou=0.3,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=256,
pos_fraction=0.5,
neg_pos_ub=-1,
add_gt_as_proposals=False),
allowed_border=-1,
pos_weight=-1,
debug=False),
rpn_proposal=dict(
nms_pre=2000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.5,
min_pos_iou=0.5,
match_low_quality=True,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
mask_size=28,
pos_weight=-1,
debug=False)),
test_cfg=dict(
rpn=dict(
nms_pre=1000,
max_per_img=1000,
nms=dict(type='nms', iou_threshold=0.7),
min_bbox_size=0),
rcnn=dict(
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100,
mask_thr_binary=0.5)))
configs/_base_/models/retinanet_r50_fpn.py 0 → 100644
View file @ a8562a56
# model settings
model = dict(
type='RetinaNet',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True,
pad_size_divisor=32),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_input',
num_outs=5),
bbox_head=dict(
type='RetinaHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
anchor_generator=dict(
type='AnchorGenerator',
octave_base_scale=4,
scales_per_octave=3,
ratios=[0.5, 1.0, 2.0],
strides=[8, 16, 32, 64, 128]),
bbox_coder=dict(
type='DeltaXYWHBBoxCoder',
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0]),
loss_cls=dict(
type='FocalLoss',
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0),
loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
# model training and testing settings
train_cfg=dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.5,
neg_iou_thr=0.4,
min_pos_iou=0,
ignore_iof_thr=-1),
sampler=dict(
type='PseudoSampler'), # Focal loss should use PseudoSampler
allowed_border=-1,
pos_weight=-1,
debug=False),
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.5),
max_per_img=100))
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment