Skip to content

GitLab

Commit 26b83c4a authored by dengjb's avatar dengjb
Browse files

update codes

parent 2f6baaee
Pipeline #1045 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 1900 additions and 0 deletions
mmdet/configs/common/lsj_100e_coco_detection.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmengine.dataset.sampler import DefaultSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import CocoDataset, RepeatDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (FilterAnnotations,
LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
Pad, RandomCrop, RandomFlip,
RandomResize, Resize)
from mmdet.evaluation import CocoMetric
# dataset settings
dataset_type = CocoDataset
data_root = 'data/coco/'
image_size = (1024, 1024)
backend_args = None
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type=RandomResize,
scale=image_size,
ratio_range=(0.1, 2.0),
keep_ratio=True),
dict(
type=RandomCrop,
crop_type='absolute_range',
crop_size=image_size,
recompute_bbox=True,
allow_negative_crop=True),
dict(type=FilterAnnotations, min_gt_bbox_wh=(1e-2, 1e-2)),
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),
dict(type=LoadAnnotations, with_bbox=True),
dict(
type=PackDetInputs,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
# Use RepeatDataset to speed up training
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
sampler=dict(type=DefaultSampler, shuffle=True),
dataset=dict(
type=RepeatDataset,
times=4, # simply change this from 2 to 16 for 50e - 400e training.
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=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/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', 'segm'],
format_only=False,
backend_args=backend_args)
test_evaluator = val_evaluator
max_epochs = 25
train_cfg = dict(
type=EpochBasedTrainLoop, max_epochs=max_epochs, val_interval=5)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)
# optimizer assumes bs=64
optim_wrapper = dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.1, momentum=0.9, weight_decay=0.00004))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.067, by_epoch=False, begin=0, end=500),
dict(
type=MultiStepLR,
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[22, 24],
gamma=0.1)
]
# only keep latest 2 checkpoints
default_hooks.update(dict(checkpoint=dict(max_keep_ckpts=2)))
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (32 GPUs) x (2 samples per GPU)
auto_scale_lr = dict(base_batch_size=64)
mmdet/configs/common/lsj_100e_coco_instance.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmengine.dataset.sampler import DefaultSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import CocoDataset, RepeatDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (FilterAnnotations,
LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
Pad, RandomCrop, RandomFlip,
RandomResize, Resize)
from mmdet.evaluation import CocoMetric
# dataset settings
dataset_type = CocoDataset
data_root = 'data/coco/'
image_size = (1024, 1024)
backend_args = None
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type=RandomResize,
scale=image_size,
ratio_range=(0.1, 2.0),
keep_ratio=True),
dict(
type=RandomCrop,
crop_type='absolute_range',
crop_size=image_size,
recompute_bbox=True,
allow_negative_crop=True),
dict(type=FilterAnnotations, min_gt_bbox_wh=(1e-2, 1e-2)),
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),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type=PackDetInputs,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
# Use RepeatDataset to speed up training
train_dataloader = dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
sampler=dict(type=DefaultSampler, shuffle=True),
dataset=dict(
type=RepeatDataset,
times=4, # simply change this from 2 to 16 for 50e - 400e training.
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=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/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', 'segm'],
format_only=False,
backend_args=backend_args)
test_evaluator = val_evaluator
max_epochs = 25
train_cfg = dict(
type=EpochBasedTrainLoop, max_epochs=max_epochs, val_interval=5)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)
# optimizer assumes bs=64
optim_wrapper = dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.1, momentum=0.9, weight_decay=0.00004))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.067, by_epoch=False, begin=0, end=500),
dict(
type=MultiStepLR,
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[22, 24],
gamma=0.1)
]
# only keep latest 2 checkpoints
default_hooks.update(dict(checkpoint=dict(max_keep_ckpts=2)))
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (32 GPUs) x (2 samples per GPU)
auto_scale_lr = dict(base_batch_size=64)
mmdet/configs/common/lsj_200e_coco_detection.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .lsj_100e_coco_detection import *
# 8x25=200e
train_dataloader.update(dict(dataset=dict(times=8)))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.067, by_epoch=False, begin=0, end=1000),
dict(
type=MultiStepLR,
begin=0,
end=25,
by_epoch=True,
milestones=[22, 24],
gamma=0.1)
]
mmdet/configs/common/lsj_200e_coco_instance.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .lsj_100e_coco_instance import *
# 8x25=200e
train_dataloader.update(dict(dataset=dict(times=8)))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.067, by_epoch=False, begin=0, end=1000),
dict(
type=MultiStepLR,
begin=0,
end=25,
by_epoch=True,
milestones=[22, 24],
gamma=0.1)
]
mmdet/configs/common/ms_3x_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmcv.transforms import RandomResize
from mmengine.dataset import RepeatDataset
from mmengine.dataset.sampler import DefaultSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import AspectRatioBatchSampler, CocoDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import RandomFlip, Resize
from mmdet.evaluation import CocoMetric
# 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
# In mstrain 3x config, img_scale=[(1333, 640), (1333, 800)],
# multiscale_mode='range'
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True),
dict(type=RandomResize, scale=[(1333, 640), (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),
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,
pin_memory=True,
sampler=dict(type=DefaultSampler, shuffle=True),
batch_sampler=dict(type=AspectRatioBatchSampler),
dataset=dict(
type=RepeatDataset,
times=3,
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=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/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',
backend_args=backend_args)
test_evaluator = val_evaluator
# training schedule for 3x with `RepeatDataset`
train_cfg = dict(type=EpochBasedTrainLoop, max_iters=12, val_interval=1)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=500),
dict(
type=MultiStepLR,
begin=0,
end=12,
by_epoch=False,
milestones=[9, 11],
gamma=0.1)
]
# optimizer
optim_wrapper = dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.02, momentum=0.9, weight_decay=0.0001))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=16)
mmdet/configs/common/ms_3x_coco_instance.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmcv.transforms import RandomChoiceResize
from mmengine.dataset import RepeatDataset
from mmengine.dataset.sampler import DefaultSampler, InfiniteSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import IterBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import AspectRatioBatchSampler, CocoDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (FilterAnnotations,
LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
Pad, RandomCrop, RandomFlip,
RandomResize, Resize)
from mmdet.evaluation import CocoMetric
# 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
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type='RandomResize', scale=[(1333, 640), (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),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type=PackDetInputs,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader.update(
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=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=train_pipeline,
backend_args=backend_args))))
val_dataloader.update(
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.update(
dict(
type=CocoMetric,
ann_file=data_root + 'annotations/instances_val2017.json',
metric='bbox',
backend_args=backend_args))
test_evaluator = val_evaluator
# training schedule for 3x with `RepeatDataset`
train_cfg.update(dict(type=EpochBasedTrainLoop, max_epochs=12, val_interval=1))
val_cfg.update(dict(type=ValLoop))
test_cfg.update(dict(type=TestLoop))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=500),
dict(
type=MultiStepLR,
begin=0,
end=12,
by_epoch=False,
milestones=[9, 11],
gamma=0.1)
]
# optimizer
optim_wrapper.update(
dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.02, momentum=0.9, weight_decay=0.0001)))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr.update(dict(enable=False, base_batch_size=16))
mmdet/configs/common/ms_90k_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmcv.transforms import RandomChoiceResize
from mmengine.dataset import RepeatDataset
from mmengine.dataset.sampler import DefaultSampler, InfiniteSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import IterBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import AspectRatioBatchSampler, CocoDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (FilterAnnotations,
LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
Pad, RandomCrop, RandomFlip,
RandomResize, Resize)
from mmdet.evaluation import CocoMetric
# 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
# Align with Detectron2
backend = 'pillow'
train_pipeline = [
dict(
type=LoadImageFromFile,
backend_args=backend_args,
imdecode_backend=backend),
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,
backend=backend),
dict(type=RandomFlip, prob=0.5),
dict(type=PackDetInputs)
]
test_pipeline = [
dict(
type=LoadImageFromFile,
backend_args=backend_args,
imdecode_backend=backend),
dict(type=Resize, scale=(1333, 800), keep_ratio=True, backend=backend),
dict(type=LoadAnnotations, with_bbox=True),
dict(
type=PackDetInputs,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader.update(
dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
pin_memory=True,
sampler=dict(type=InfiniteSampler, shuffle=True),
batch_sampler=dict(type=AspectRatioBatchSampler),
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=train_pipeline,
backend_args=backend_args)))
val_dataloader.update(
dict(
batch_size=1,
num_workers=2,
persistent_workers=True,
drop_last=False,
pin_memory=True,
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.update(
dict(
type=CocoMetric,
ann_file=data_root + 'annotations/instances_val2017.json',
metric='bbox',
format_only=False,
backend_args=backend_args))
test_evaluator = val_evaluator
# training schedule for 90k
max_iter = 90000
train_cfg.update(
dict(type=IterBasedTrainLoop, max_iters=max_iter, val_interval=10000))
val_cfg.update(dict(type=ValLoop))
test_cfg.update(dict(type=TestLoop))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=1000),
dict(
type=MultiStepLR,
begin=0,
end=max_iter,
by_epoch=False,
milestones=[60000, 80000],
gamma=0.1)
]
# optimizer
optim_wrapper.update(
dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.02, momentum=0.9, weight_decay=0.0001)))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr.update(dict(enable=False, base_batch_size=16))
default_hooks.update(dict(checkpoint=dict(by_epoch=False, interval=10000)))
log_processor.update(dict(by_epoch=False))
mmdet/configs/common/ms_poly_3x_coco_instance.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmcv.transforms import RandomChoiceResize
from mmengine.dataset import RepeatDataset
from mmengine.dataset.sampler import DefaultSampler, InfiniteSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import IterBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import AspectRatioBatchSampler, CocoDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (FilterAnnotations,
LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
Pad, RandomCrop, RandomFlip,
RandomResize, Resize)
from mmdet.evaluation import CocoMetric
# 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
# In mstrain 3x config, img_scale=[(1333, 640), (1333, 800)],
# multiscale_mode='range'
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(
type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
dict(
type='RandomResize', scale=[(1333, 640), (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),
dict(
type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
dict(
type=PackDetInputs,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader.update(
dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
pin_memory=True,
sampler=dict(type=DefaultSampler, shuffle=True),
batch_sampler=dict(type=AspectRatioBatchSampler),
dataset=dict(
type=RepeatDataset,
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=train_pipeline,
backend_args=backend_args)))
val_dataloader.update(
dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
drop_last=False,
pin_memory=True,
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.update(
dict(
type=CocoMetric,
ann_file=data_root + 'annotations/instances_val2017.json',
metric=['bbox', 'segm'],
backend_args=backend_args))
test_evaluator = val_evaluator
# training schedule for 3x with `RepeatDataset`
train_cfg.update(dict(type=EpochBasedTrainLoop, max_iters=12, val_interval=1))
val_cfg.update(dict(type=ValLoop))
test_cfg.update(dict(type=TestLoop))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=500),
dict(
type=MultiStepLR,
begin=0,
end=12,
by_epoch=False,
milestones=[9, 11],
gamma=0.1)
]
# optimizer
optim_wrapper.update(
dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.02, momentum=0.9, weight_decay=0.0001)))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr.update(dict(enable=False, base_batch_size=16))
mmdet/configs/common/ms_poly_90k_coco_instance.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmcv.transforms import RandomChoiceResize
from mmengine.dataset import RepeatDataset
from mmengine.dataset.sampler import DefaultSampler, InfiniteSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import IterBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import AspectRatioBatchSampler, CocoDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (FilterAnnotations,
LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
Pad, RandomCrop, RandomFlip,
RandomResize, Resize)
from mmdet.evaluation import CocoMetric
# 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
# Align with Detectron2
backend = 'pillow'
train_pipeline = [
dict(
type=LoadImageFromFile,
backend_args=backend_args,
imdecode_backend=backend),
dict(
type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
dict(
type=RandomChoiceResize,
scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
(1333, 768), (1333, 800)],
keep_ratio=True,
backend=backend),
dict(type=RandomFlip, prob=0.5),
dict(type=PackDetInputs)
]
test_pipeline = [
dict(
type=LoadImageFromFile,
backend_args=backend_args,
imdecode_backend=backend),
dict(type=Resize, scale=(1333, 800), keep_ratio=True, backend=backend),
dict(
type=LoadAnnotations, with_bbox=True, with_mask=True, poly2mask=False),
dict(
type=PackDetInputs,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader.update(
dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
pin_memory=True,
sampler=dict(type=InfiniteSampler, shuffle=True),
batch_sampler=dict(type=AspectRatioBatchSampler),
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=train_pipeline,
backend_args=backend_args)))
val_dataloader.update(
dict(
batch_size=1,
num_workers=2,
persistent_workers=True,
drop_last=False,
pin_memory=True,
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.update(
dict(
type=CocoMetric,
ann_file=data_root + 'annotations/instances_val2017.json',
metric=['bbox', 'segm'],
format_only=False,
backend_args=backend_args))
test_evaluator = val_evaluator
# training schedule for 90k
max_iter = 90000
train_cfg.update(
dict(type=IterBasedTrainLoop, max_iters=max_iter, val_interval=10000))
val_cfg.update(dict(type=ValLoop))
test_cfg.update(dict(type=TestLoop))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=1000),
dict(
type=MultiStepLR,
begin=0,
end=max_iter,
by_epoch=False,
milestones=[60000, 80000],
gamma=0.1)
]
# optimizer
optim_wrapper.update(
dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.02, momentum=0.9, weight_decay=0.0001)))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr.update(dict(enable=False, base_batch_size=16))
default_hooks.update(dict(checkpoint=dict(by_epoch=False, interval=10000)))
log_processor.update(dict(by_epoch=False))
mmdet/configs/common/ssj_270_coco_instance.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.default_runtime import *
from mmcv.transforms import RandomChoiceResize
from mmengine.dataset import RepeatDataset
from mmengine.dataset.sampler import DefaultSampler, InfiniteSampler
from mmengine.optim import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import IterBasedTrainLoop, TestLoop, ValLoop
from torch.optim import SGD
from mmdet.datasets import AspectRatioBatchSampler, CocoDataset
from mmdet.datasets.transforms.formatting import PackDetInputs
from mmdet.datasets.transforms.loading import (FilterAnnotations,
LoadAnnotations,
LoadImageFromFile)
from mmdet.datasets.transforms.transforms import (CachedMixUp, CachedMosaic,
Pad, RandomCrop, RandomFlip,
RandomResize, Resize)
from mmdet.evaluation import CocoMetric
# 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
# Standard Scale Jittering (SSJ) resizes and crops an image
# with a resize range of 0.8 to 1.25 of the original image size.
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type=RandomResize,
scale=image_size,
ratio_range=(0.8, 1.25),
keep_ratio=True),
dict(
type='RandomCrop',
crop_type='absolute_range',
crop_size=image_size,
recompute_bbox=True,
allow_negative_crop=True),
dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
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),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type=PackDetInputs,
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'scale_factor'))
]
train_dataloader.update(
dict(
batch_size=2,
num_workers=2,
persistent_workers=True,
sampler=dict(type=InfiniteSampler),
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=train_pipeline,
backend_args=backend_args)))
val_dataloader.update(
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.update(
dict(
type=CocoMetric,
ann_file=data_root + 'annotations/instances_val2017.json',
metric=['bbox', 'segm'],
format_only=False,
backend_args=backend_args))
test_evaluator = val_evaluator
val_evaluator = dict(
type=CocoMetric,
ann_file=data_root + 'annotations/instances_val2017.json',
metric=['bbox', 'segm'],
format_only=False,
backend_args=backend_args)
test_evaluator = val_evaluator
# The model is trained by 270k iterations with batch_size 64,
# which is roughly equivalent to 144 epochs.
max_iter = 270000
train_cfg.update(
dict(type=IterBasedTrainLoop, max_iters=max_iter, val_interval=10000))
val_cfg.update(dict(type=ValLoop))
test_cfg.update(dict(type=TestLoop))
# learning rate
param_scheduler = [
dict(type=LinearLR, start_factor=0.001, by_epoch=False, begin=0, end=1000),
dict(
type=MultiStepLR,
begin=0,
end=max_iter,
by_epoch=False,
milestones=[243000, 256500, 263250],
gamma=0.1)
]
# optimizer
optim_wrapper.update(
dict(
type=OptimWrapper,
optimizer=dict(type=SGD, lr=0.1, momentum=0.9, weight_decay=0.00004)))
# Default setting for scaling LR automatically
# - `enable` means enable scaling LR automatically
# or not by default.
# - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr.update(dict(base_batch_size=64))
default_hooks.update(dict(checkpoint=dict(by_epoch=False, interval=10000)))
log_processor.update(dict(by_epoch=False))
mmdet/configs/common/ssj_scp_270k_coco_instance.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .ssj_270_coco_instance import *
from mmdet.datasets import MultiImageMixDataset
from mmdet.datasets.transforms import CopyPaste
# dataset settings
dataset_type = CocoDataset
data_root = 'dataset/coco_mini/'
image_size = (1024, 1024)
# 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
# Standard Scale Jittering (SSJ) resizes and crops an image
# with a resize range of 0.8 to 1.25 of the original image size.
load_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True, with_mask=True),
dict(
type=RandomResize,
scale=image_size,
ratio_range=(0.8, 1.25),
keep_ratio=True),
dict(
type='RandomCrop',
crop_type='absolute_range',
crop_size=image_size,
recompute_bbox=True,
allow_negative_crop=True),
dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),
dict(type=RandomFlip, prob=0.5),
dict(type=Pad, size=image_size),
]
train_pipeline = [
dict(type=CopyPaste, max_num_pasted=100),
dict(type=PackDetInputs)
]
train_dataloader.update(
dict(
type=MultiImageMixDataset,
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=load_pipeline,
backend_args=backend_args),
pipeline=train_pipeline))
mmdet/configs/deformable_detr/deformable_detr_r50_16xb2_50e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .._base_.datasets.coco_detection import *
from .._base_.default_runtime import *
from mmcv.transforms import LoadImageFromFile, RandomChoice, RandomChoiceResize
from mmengine.optim.optimizer import OptimWrapper
from mmengine.optim.scheduler import MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim.adamw import AdamW
from mmdet.datasets.transforms import (LoadAnnotations, PackDetInputs,
RandomCrop, RandomFlip, Resize)
from mmdet.models.backbones import ResNet
from mmdet.models.data_preprocessors import DetDataPreprocessor
from mmdet.models.dense_heads import DeformableDETRHead
from mmdet.models.detectors import DeformableDETR
from mmdet.models.losses import FocalLoss, GIoULoss, L1Loss
from mmdet.models.necks import ChannelMapper
from mmdet.models.task_modules import (BBoxL1Cost, FocalLossCost,
HungarianAssigner, IoUCost)
model = dict(
type=DeformableDETR,
num_queries=300,
num_feature_levels=4,
with_box_refine=False,
as_two_stage=False,
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=1),
backbone=dict(
type=ResNet,
depth=50,
num_stages=4,
out_indices=(1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=False),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type=ChannelMapper,
in_channels=[512, 1024, 2048],
kernel_size=1,
out_channels=256,
act_cfg=None,
norm_cfg=dict(type='GN', num_groups=32),
num_outs=4),
encoder=dict( # DeformableDetrTransformerEncoder
num_layers=6,
layer_cfg=dict( # DeformableDetrTransformerEncoderLayer
self_attn_cfg=dict( # MultiScaleDeformableAttention
embed_dims=256,
batch_first=True),
ffn_cfg=dict(
embed_dims=256, feedforward_channels=1024, ffn_drop=0.1))),
decoder=dict( # DeformableDetrTransformerDecoder
num_layers=6,
return_intermediate=True,
layer_cfg=dict( # DeformableDetrTransformerDecoderLayer
self_attn_cfg=dict( # MultiheadAttention
embed_dims=256,
num_heads=8,
dropout=0.1,
batch_first=True),
cross_attn_cfg=dict( # MultiScaleDeformableAttention
embed_dims=256,
batch_first=True),
ffn_cfg=dict(
embed_dims=256, feedforward_channels=1024, ffn_drop=0.1)),
post_norm_cfg=None),
positional_encoding=dict(num_feats=128, normalize=True, offset=-0.5),
bbox_head=dict(
type=DeformableDETRHead,
num_classes=80,
sync_cls_avg_factor=True,
loss_cls=dict(
type=FocalLoss,
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=2.0),
loss_bbox=dict(type=L1Loss, loss_weight=5.0),
loss_iou=dict(type=GIoULoss, loss_weight=2.0)),
# training and testing settings
train_cfg=dict(
assigner=dict(
type=HungarianAssigner,
match_costs=[
dict(type=FocalLossCost, weight=2.0),
dict(type=BBoxL1Cost, weight=5.0, box_format='xywh'),
dict(type=IoUCost, iou_mode='giou', weight=2.0)
])),
test_cfg=dict(max_per_img=100))
# train_pipeline, NOTE the img_scale and the Pad's size_divisor is different
# from the default setting in mmdet.
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True),
dict(type=RandomFlip, prob=0.5),
dict(
type=RandomChoice,
transforms=[
[
dict(
type=RandomChoiceResize,
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
resize_type=Resize,
keep_ratio=True)
],
[
dict(
type=RandomChoiceResize,
# The radio of all image in train dataset < 7
# follow the original implement
scales=[(400, 4200), (500, 4200), (600, 4200)],
resize_type=Resize,
keep_ratio=True),
dict(
type=RandomCrop,
crop_type='absolute_range',
crop_size=(384, 600),
allow_negative_crop=True),
dict(
type=RandomChoiceResize,
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
resize_type=Resize,
keep_ratio=True)
]
]),
dict(type=PackDetInputs)
]
train_dataloader.update(
dict(
dataset=dict(
filter_cfg=dict(filter_empty_gt=False), pipeline=train_pipeline)))
# optimizer
optim_wrapper = dict(
type=OptimWrapper,
optimizer=dict(type=AdamW, lr=0.0002, weight_decay=0.0001),
clip_grad=dict(max_norm=0.1, norm_type=2),
paramwise_cfg=dict(
custom_keys={
'backbone': dict(lr_mult=0.1),
'sampling_offsets': dict(lr_mult=0.1),
'reference_points': dict(lr_mult=0.1)
}))
# learning policy
max_epochs = 50
train_cfg = dict(
type=EpochBasedTrainLoop, max_epochs=max_epochs, val_interval=1)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)
param_scheduler = [
dict(
type=MultiStepLR,
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[40],
gamma=0.1)
]
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (16 GPUs) x (2 samples per GPU)
auto_scale_lr = dict(base_batch_size=32)
mmdet/configs/deformable_detr/deformable_detr_refine_r50_16xb2_50e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .deformable_detr_r50_16xb2_50e_coco import *
model.update(dict(with_box_refine=True))
mmdet/configs/deformable_detr/deformable_detr_refine_twostage_r50_16xb2_50e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
# Please refer to https://mmengine.readthedocs.io/en/latest/advanced_tutorials/config.html#a-pure-python-style-configuration-file-beta for more details. # noqa
# mmcv >= 2.0.1
# mmengine >= 0.8.0
from mmengine.config import read_base
with read_base():
from .deformable_detr_refine_r50_16xb2_50e_coco import *
model.update(dict(as_two_stage=True))
mmdet/configs/detr/detr_r101_8xb2_500e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.config import read_base
from mmengine.model.weight_init import PretrainedInit
with read_base():
from .detr_r50_8xb2_500e_coco import *
model.update(
dict(
backbone=dict(
depth=101,
init_cfg=dict(
type=PretrainedInit, checkpoint='torchvision://resnet101'))))
mmdet/configs/detr/detr_r18_8xb2_500e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.config import read_base
from mmengine.model.weight_init import PretrainedInit
with read_base():
from .detr_r50_8xb2_500e_coco import *
model.update(
dict(
backbone=dict(
depth=18,
init_cfg=dict(
type=PretrainedInit, checkpoint='torchvision://resnet18')),
neck=dict(in_channels=[512])))
mmdet/configs/detr/detr_r50_8xb2_150e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.transforms import RandomChoice, RandomChoiceResize
from mmcv.transforms.loading import LoadImageFromFile
from mmengine.config import read_base
from mmengine.model.weight_init import PretrainedInit
from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.nn.modules.activation import ReLU
from torch.nn.modules.batchnorm import BatchNorm2d
from torch.optim.adamw import AdamW
from mmdet.datasets.transforms import (LoadAnnotations, PackDetInputs,
RandomCrop, RandomFlip, Resize)
from mmdet.models import (DETR, ChannelMapper, DetDataPreprocessor, DETRHead,
ResNet)
from mmdet.models.losses.cross_entropy_loss import CrossEntropyLoss
from mmdet.models.losses.iou_loss import GIoULoss
from mmdet.models.losses.smooth_l1_loss import L1Loss
from mmdet.models.task_modules import (BBoxL1Cost, ClassificationCost,
HungarianAssigner, IoUCost)
with read_base():
from .._base_.datasets.coco_detection import *
from .._base_.default_runtime import *
model = dict(
type=DETR,
num_queries=100,
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=1),
backbone=dict(
type=ResNet,
depth=50,
num_stages=4,
out_indices=(3, ),
frozen_stages=1,
norm_cfg=dict(type=BatchNorm2d, requires_grad=False),
norm_eval=True,
style='pytorch',
init_cfg=dict(
type=PretrainedInit, checkpoint='torchvision://resnet50')),
neck=dict(
type=ChannelMapper,
in_channels=[2048],
kernel_size=1,
out_channels=256,
act_cfg=None,
norm_cfg=None,
num_outs=1),
encoder=dict( # DetrTransformerEncoder
num_layers=6,
layer_cfg=dict( # DetrTransformerEncoderLayer
self_attn_cfg=dict( # MultiheadAttention
embed_dims=256,
num_heads=8,
dropout=0.1,
batch_first=True),
ffn_cfg=dict(
embed_dims=256,
feedforward_channels=2048,
num_fcs=2,
ffn_drop=0.1,
act_cfg=dict(type=ReLU, inplace=True)))),
decoder=dict( # DetrTransformerDecoder
num_layers=6,
layer_cfg=dict( # DetrTransformerDecoderLayer
self_attn_cfg=dict( # MultiheadAttention
embed_dims=256,
num_heads=8,
dropout=0.1,
batch_first=True),
cross_attn_cfg=dict( # MultiheadAttention
embed_dims=256,
num_heads=8,
dropout=0.1,
batch_first=True),
ffn_cfg=dict(
embed_dims=256,
feedforward_channels=2048,
num_fcs=2,
ffn_drop=0.1,
act_cfg=dict(type=ReLU, inplace=True))),
return_intermediate=True),
positional_encoding=dict(num_feats=128, normalize=True),
bbox_head=dict(
type=DETRHead,
num_classes=80,
embed_dims=256,
loss_cls=dict(
type=CrossEntropyLoss,
bg_cls_weight=0.1,
use_sigmoid=False,
loss_weight=1.0,
class_weight=1.0),
loss_bbox=dict(type=L1Loss, loss_weight=5.0),
loss_iou=dict(type=GIoULoss, loss_weight=2.0)),
# training and testing settings
train_cfg=dict(
assigner=dict(
type=HungarianAssigner,
match_costs=[
dict(type=ClassificationCost, weight=1.),
dict(type=BBoxL1Cost, weight=5.0, box_format='xywh'),
dict(type=IoUCost, iou_mode='giou', weight=2.0)
])),
test_cfg=dict(max_per_img=100))
# train_pipeline, NOTE the img_scale and the Pad's size_divisor is different
# from the default setting in mmdet.
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True),
dict(type=RandomFlip, prob=0.5),
dict(
type=RandomChoice,
transforms=[[
dict(
type=RandomChoiceResize,
resize_type=Resize,
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
keep_ratio=True)
],
[
dict(
type=RandomChoiceResize,
resize_type=Resize,
scales=[(400, 1333), (500, 1333), (600, 1333)],
keep_ratio=True),
dict(
type=RandomCrop,
crop_type='absolute_range',
crop_size=(384, 600),
allow_negative_crop=True),
dict(
type=RandomChoiceResize,
resize_type=Resize,
scales=[(480, 1333), (512, 1333), (544, 1333),
(576, 1333), (608, 1333), (640, 1333),
(672, 1333), (704, 1333), (736, 1333),
(768, 1333), (800, 1333)],
keep_ratio=True)
]]),
dict(type=PackDetInputs)
]
train_dataloader.update(dataset=dict(pipeline=train_pipeline))
# optimizer
optim_wrapper = dict(
type=OptimWrapper,
optimizer=dict(type=AdamW, lr=0.0001, weight_decay=0.0001),
clip_grad=dict(max_norm=0.1, norm_type=2),
paramwise_cfg=dict(
custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)}))
# learning policy
max_epochs = 150
train_cfg = dict(
type=EpochBasedTrainLoop, max_epochs=max_epochs, val_interval=1)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)
param_scheduler = [
dict(
type=MultiStepLR,
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[100],
gamma=0.1)
]
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (2 samples per GPU)
auto_scale_lr = dict(base_batch_size=16)
mmdet/configs/detr/detr_r50_8xb2_500e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.config import read_base
from mmengine.optim.scheduler.lr_scheduler import MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop
with read_base():
from .detr_r50_8xb2_150e_coco import *
# learning policy
max_epochs = 500
train_cfg.update(
type=EpochBasedTrainLoop, max_epochs=max_epochs, val_interval=10)
param_scheduler = [
dict(
type=MultiStepLR,
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[334],
gamma=0.1)
]
# only keep latest 2 checkpoints
default_hooks.update(checkpoint=dict(max_keep_ckpts=2))
mmdet/configs/dino/dino_4scale_r50_8xb2_12e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.transforms import RandomChoice, RandomChoiceResize
from mmcv.transforms.loading import LoadImageFromFile
from mmengine.config import read_base
from mmengine.model.weight_init import PretrainedInit
from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.nn.modules.batchnorm import BatchNorm2d
from torch.nn.modules.normalization import GroupNorm
from torch.optim.adamw import AdamW
from mmdet.datasets.transforms import (LoadAnnotations, PackDetInputs,
RandomCrop, RandomFlip, Resize)
from mmdet.models import (DINO, ChannelMapper, DetDataPreprocessor, DINOHead,
ResNet)
from mmdet.models.losses.focal_loss import FocalLoss
from mmdet.models.losses.iou_loss import GIoULoss
from mmdet.models.losses.smooth_l1_loss import L1Loss
from mmdet.models.task_modules import (BBoxL1Cost, FocalLossCost,
HungarianAssigner, IoUCost)
with read_base():
from .._base_.datasets.coco_detection import *
from .._base_.default_runtime import *
model = dict(
type=DINO,
num_queries=900, # num_matching_queries
with_box_refine=True,
as_two_stage=True,
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=1),
backbone=dict(
type=ResNet,
depth=50,
num_stages=4,
out_indices=(1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type=BatchNorm2d, requires_grad=False),
norm_eval=True,
style='pytorch',
init_cfg=dict(
type=PretrainedInit, checkpoint='torchvision://resnet50')),
neck=dict(
type=ChannelMapper,
in_channels=[512, 1024, 2048],
kernel_size=1,
out_channels=256,
act_cfg=None,
norm_cfg=dict(type=GroupNorm, num_groups=32),
num_outs=4),
encoder=dict(
num_layers=6,
layer_cfg=dict(
self_attn_cfg=dict(embed_dims=256, num_levels=4,
dropout=0.0), # 0.1 for DeformDETR
ffn_cfg=dict(
embed_dims=256,
feedforward_channels=2048, # 1024 for DeformDETR
ffn_drop=0.0))), # 0.1 for DeformDETR
decoder=dict(
num_layers=6,
return_intermediate=True,
layer_cfg=dict(
self_attn_cfg=dict(embed_dims=256, num_heads=8,
dropout=0.0), # 0.1 for DeformDETR
cross_attn_cfg=dict(embed_dims=256, num_levels=4,
dropout=0.0), # 0.1 for DeformDETR
ffn_cfg=dict(
embed_dims=256,
feedforward_channels=2048, # 1024 for DeformDETR
ffn_drop=0.0)), # 0.1 for DeformDETR
post_norm_cfg=None),
positional_encoding=dict(
num_feats=128,
normalize=True,
offset=0.0, # -0.5 for DeformDETR
temperature=20), # 10000 for DeformDETR
bbox_head=dict(
type=DINOHead,
num_classes=80,
sync_cls_avg_factor=True,
loss_cls=dict(
type=FocalLoss,
use_sigmoid=True,
gamma=2.0,
alpha=0.25,
loss_weight=1.0), # 2.0 in DeformDETR
loss_bbox=dict(type=L1Loss, loss_weight=5.0),
loss_iou=dict(type=GIoULoss, loss_weight=2.0)),
dn_cfg=dict( # TODO: Move to model.train_cfg ?
label_noise_scale=0.5,
box_noise_scale=1.0, # 0.4 for DN-DETR
group_cfg=dict(dynamic=True, num_groups=None,
num_dn_queries=100)), # TODO: half num_dn_queries
# training and testing settings
train_cfg=dict(
assigner=dict(
type=HungarianAssigner,
match_costs=[
dict(type=FocalLossCost, weight=2.0),
dict(type=BBoxL1Cost, weight=5.0, box_format='xywh'),
dict(type=IoUCost, iou_mode='giou', weight=2.0)
])),
test_cfg=dict(max_per_img=300)) # 100 for DeformDETR
# train_pipeline, NOTE the img_scale and the Pad's size_divisor is different
# from the default setting in mmdet.
train_pipeline = [
dict(type=LoadImageFromFile, backend_args=backend_args),
dict(type=LoadAnnotations, with_bbox=True),
dict(type=RandomFlip, prob=0.5),
dict(
type=RandomChoice,
transforms=[
[
dict(
type=RandomChoiceResize,
resize_type=Resize,
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
keep_ratio=True)
],
[
dict(
type=RandomChoiceResize,
resize_type=Resize,
# The radio of all image in train dataset < 7
# follow the original implement
scales=[(400, 4200), (500, 4200), (600, 4200)],
keep_ratio=True),
dict(
type=RandomCrop,
crop_type='absolute_range',
crop_size=(384, 600),
allow_negative_crop=True),
dict(
type=RandomChoiceResize,
resize_type=Resize,
scales=[(480, 1333), (512, 1333), (544, 1333), (576, 1333),
(608, 1333), (640, 1333), (672, 1333), (704, 1333),
(736, 1333), (768, 1333), (800, 1333)],
keep_ratio=True)
]
]),
dict(type=PackDetInputs)
]
train_dataloader.update(
dataset=dict(
filter_cfg=dict(filter_empty_gt=False), pipeline=train_pipeline))
# optimizer
optim_wrapper = dict(
type=OptimWrapper,
optimizer=dict(
type=AdamW,
lr=0.0001, # 0.0002 for DeformDETR
weight_decay=0.0001),
clip_grad=dict(max_norm=0.1, norm_type=2),
paramwise_cfg=dict(custom_keys={'backbone': dict(lr_mult=0.1)})
) # custom_keys contains sampling_offsets and reference_points in DeformDETR # noqa
# learning policy
max_epochs = 12
train_cfg = dict(
type=EpochBasedTrainLoop, max_epochs=max_epochs, val_interval=1)
val_cfg = dict(type=ValLoop)
test_cfg = dict(type=TestLoop)
param_scheduler = [
dict(
type=MultiStepLR,
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[11],
gamma=0.1)
]
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (2 samples per GPU)
auto_scale_lr = dict(base_batch_size=16)
mmdet/configs/dino/dino_4scale_r50_8xb2_24e_coco.py 0 → 100644
View file @ 26b83c4a
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.config import read_base
from mmengine.runner.loops import EpochBasedTrainLoop
with read_base():
from .dino_4scale_r50_8xb2_12e_coco import *
max_epochs = 24
train_cfg.update(
dict(type=EpochBasedTrainLoop, max_epochs=max_epochs, val_interval=1))
param_scheduler[0].update(dict(milestones=[20]))
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