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 2074 additions and 0 deletions
mmdet/configs/_base_/models/cascade_rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.ops import RoIAlign, nms
from torch.nn import BatchNorm2d
from mmdet.models.backbones.resnet import ResNet
from mmdet.models.data_preprocessors.data_preprocessor import \
DetDataPreprocessor
from mmdet.models.dense_heads.rpn_head import RPNHead
from mmdet.models.detectors.cascade_rcnn import CascadeRCNN
from mmdet.models.losses.cross_entropy_loss import CrossEntropyLoss
from mmdet.models.losses.smooth_l1_loss import SmoothL1Loss
from mmdet.models.necks.fpn import FPN
from mmdet.models.roi_heads.bbox_heads.convfc_bbox_head import \
Shared2FCBBoxHead
from mmdet.models.roi_heads.cascade_roi_head import CascadeRoIHead
from mmdet.models.roi_heads.roi_extractors.single_level_roi_extractor import \
SingleRoIExtractor
from mmdet.models.task_modules.assigners.max_iou_assigner import MaxIoUAssigner
from mmdet.models.task_modules.coders.delta_xywh_bbox_coder import \
DeltaXYWHBBoxCoder
from mmdet.models.task_modules.prior_generators.anchor_generator import \
AnchorGenerator
from mmdet.models.task_modules.samplers.random_sampler import RandomSampler
# 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=BatchNorm2d, 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)))
mmdet/configs/_base_/models/faster_rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.ops import RoIAlign, nms
from torch.nn import BatchNorm2d
from mmdet.models.backbones.resnet import ResNet
from mmdet.models.data_preprocessors.data_preprocessor import \
DetDataPreprocessor
from mmdet.models.dense_heads.rpn_head import RPNHead
from mmdet.models.detectors.faster_rcnn import FasterRCNN
from mmdet.models.losses.cross_entropy_loss import CrossEntropyLoss
from mmdet.models.losses.smooth_l1_loss import L1Loss
from mmdet.models.necks.fpn import FPN
from mmdet.models.roi_heads.bbox_heads.convfc_bbox_head import \
Shared2FCBBoxHead
from mmdet.models.roi_heads.roi_extractors.single_level_roi_extractor import \
SingleRoIExtractor
from mmdet.models.roi_heads.standard_roi_head import StandardRoIHead
from mmdet.models.task_modules.assigners.max_iou_assigner import MaxIoUAssigner
from mmdet.models.task_modules.coders.delta_xywh_bbox_coder import \
DeltaXYWHBBoxCoder
from mmdet.models.task_modules.prior_generators.anchor_generator import \
AnchorGenerator
from mmdet.models.task_modules.samplers.random_sampler import RandomSampler
# 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=BatchNorm2d, 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)
))
mmdet/configs/_base_/models/mask_rcnn_r50_caffe_c4.py 0 → 100644
View file @ a8562a56
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.ops import RoIAlign, nms
from mmengine.model.weight_init import PretrainedInit
from torch.nn import BatchNorm2d
from mmdet.models.backbones.resnet import ResNet
from mmdet.models.data_preprocessors.data_preprocessor import \
DetDataPreprocessor
from mmdet.models.dense_heads.rpn_head import RPNHead
from mmdet.models.detectors.mask_rcnn import MaskRCNN
from mmdet.models.layers import ResLayer
from mmdet.models.losses.cross_entropy_loss import CrossEntropyLoss
from mmdet.models.losses.smooth_l1_loss import L1Loss
from mmdet.models.roi_heads.bbox_heads.bbox_head import BBoxHead
from mmdet.models.roi_heads.mask_heads.fcn_mask_head import FCNMaskHead
from mmdet.models.roi_heads.roi_extractors.single_level_roi_extractor import \
SingleRoIExtractor
from mmdet.models.roi_heads.standard_roi_head import StandardRoIHead
from mmdet.models.task_modules.assigners.max_iou_assigner import MaxIoUAssigner
from mmdet.models.task_modules.coders.delta_xywh_bbox_coder import \
DeltaXYWHBBoxCoder
from mmdet.models.task_modules.prior_generators.anchor_generator import \
AnchorGenerator
from mmdet.models.task_modules.samplers.random_sampler import RandomSampler
# model settings
norm_cfg = dict(type=BatchNorm2d, requires_grad=False)
# model settings
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=dict(type=BatchNorm2d, requires_grad=True),
norm_eval=True,
style='caffe',
init_cfg=dict(
type=PretrainedInit,
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,
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)))
mmdet/configs/_base_/models/mask_rcnn_r50_fpn.py 0 → 100644
View file @ a8562a56
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.ops import RoIAlign, nms
from mmengine.model.weight_init import PretrainedInit
from torch.nn import BatchNorm2d
from mmdet.models.backbones.resnet import ResNet
from mmdet.models.data_preprocessors.data_preprocessor import \
DetDataPreprocessor
from mmdet.models.dense_heads.rpn_head import RPNHead
from mmdet.models.detectors.mask_rcnn import MaskRCNN
from mmdet.models.losses.cross_entropy_loss import CrossEntropyLoss
from mmdet.models.losses.smooth_l1_loss import L1Loss
from mmdet.models.necks.fpn import FPN
from mmdet.models.roi_heads.bbox_heads.convfc_bbox_head import \
Shared2FCBBoxHead
from mmdet.models.roi_heads.mask_heads.fcn_mask_head import FCNMaskHead
from mmdet.models.roi_heads.roi_extractors.single_level_roi_extractor import \
SingleRoIExtractor
from mmdet.models.roi_heads.standard_roi_head import StandardRoIHead
from mmdet.models.task_modules.assigners.max_iou_assigner import MaxIoUAssigner
from mmdet.models.task_modules.coders.delta_xywh_bbox_coder import \
DeltaXYWHBBoxCoder
from mmdet.models.task_modules.prior_generators.anchor_generator import \
AnchorGenerator
from mmdet.models.task_modules.samplers.random_sampler import RandomSampler
# 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=BatchNorm2d, requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(
type=PretrainedInit, 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)))
mmdet/configs/_base_/models/retinanet_r50_fpn.py 0 → 100644
View file @ a8562a56
# Copyright (c) OpenMMLab. All rights reserved.
from mmcv.ops import nms
from torch.nn import BatchNorm2d
from mmdet.models import (FPN, DetDataPreprocessor, FocalLoss, L1Loss, ResNet,
RetinaHead, RetinaNet)
from mmdet.models.task_modules import (AnchorGenerator, DeltaXYWHBBoxCoder,
MaxIoUAssigner, PseudoSampler)
# 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=BatchNorm2d, 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))
mmdet/configs/_base_/schedules/schedule_1x.py 0 → 100644
View file @ a8562a56
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim.sgd import SGD
# training schedule for 1x
train_cfg = dict(type=EpochBasedTrainLoop, max_epochs=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=True,
milestones=[8, 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/_base_/schedules/schedule_2x.py 0 → 100644
View file @ a8562a56
# Copyright (c) OpenMMLab. All rights reserved.
from mmengine.optim.optimizer.optimizer_wrapper import OptimWrapper
from mmengine.optim.scheduler.lr_scheduler import LinearLR, MultiStepLR
from mmengine.runner.loops import EpochBasedTrainLoop, TestLoop, ValLoop
from torch.optim.sgd import SGD
# training schedule for 1x
train_cfg = dict(type=EpochBasedTrainLoop, max_epochs=24, 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=24,
by_epoch=True,
milestones=[16, 22],
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/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.py 0 → 100644
View file @ a8562a56
# 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_instance import *
from .._base_.default_runtime import *
from .._base_.models.cascade_mask_rcnn_r50_fpn import *
from .._base_.schedules.schedule_1x import *
mmdet/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.py 0 → 100644
View file @ a8562a56
# 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 .._base_.models.cascade_rcnn_r50_fpn import *
from .._base_.schedules.schedule_1x import *
mmdet/configs/common/lsj_100e_coco_detection.py 0 → 100644
View file @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 @ a8562a56
# 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 = 'data/coco/'
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))
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