Skip to content

GitLab

Commit eb1107e4 authored by raojy's avatar raojy
Browse files

fix_mmdetection

parent 7aa442d5
Pipeline #3461 canceled with stages
Hide whitespace changes
Inline Side-by-side
Showing with 1676 additions and 0 deletions
mmde/mmdet/.mim/configs/centernet/centernet-update_r50_fpn_8xb8-amp-lsj-200e_coco.py 0 → 100644
View file @ eb1107e4
_base_ = '../common/lsj-200e_coco-detection.py'
image_size = (1024, 1024)
batch_augments = [dict(type='BatchFixedSizePad', size=image_size)]
model = dict(
type='CenterNet',
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,
batch_augments=batch_augments),
backbone=dict(
type='ResNet',
depth=50,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
norm_cfg=dict(type='BN', requires_grad=True),
norm_eval=True,
style='pytorch',
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
start_level=1,
add_extra_convs='on_output',
num_outs=5,
init_cfg=dict(type='Caffe2Xavier', layer='Conv2d'),
relu_before_extra_convs=True),
bbox_head=dict(
type='CenterNetUpdateHead',
num_classes=80,
in_channels=256,
stacked_convs=4,
feat_channels=256,
strides=[8, 16, 32, 64, 128],
loss_cls=dict(
type='GaussianFocalLoss',
pos_weight=0.25,
neg_weight=0.75,
loss_weight=1.0),
loss_bbox=dict(type='GIoULoss', loss_weight=2.0),
),
train_cfg=None,
test_cfg=dict(
nms_pre=1000,
min_bbox_size=0,
score_thr=0.05,
nms=dict(type='nms', iou_threshold=0.6),
max_per_img=100))
train_dataloader = dict(batch_size=8, num_workers=4)
# Enable automatic-mixed-precision training with AmpOptimWrapper.
optim_wrapper = dict(
type='AmpOptimWrapper',
optimizer=dict(
type='SGD', lr=0.01 * 4, momentum=0.9, weight_decay=0.00004),
paramwise_cfg=dict(norm_decay_mult=0.))
param_scheduler = [
dict(
type='LinearLR',
start_factor=0.00025,
by_epoch=False,
begin=0,
end=4000),
dict(
type='MultiStepLR',
begin=0,
end=25,
by_epoch=True,
milestones=[22, 24],
gamma=0.1)
]
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (8 samples per GPU)
auto_scale_lr = dict(base_batch_size=64)
mmde/mmdet/.mim/configs/centernet/centernet_r18-dcnv2_8xb16-crop512-140e_coco.py 0 → 100644
View file @ eb1107e4
_base_ = [
'../_base_/datasets/coco_detection.py',
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py',
'./centernet_tta.py'
]
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
# model settings
model = dict(
type='CenterNet',
data_preprocessor=dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True),
backbone=dict(
type='ResNet',
depth=18,
norm_eval=False,
norm_cfg=dict(type='BN'),
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18')),
neck=dict(
type='CTResNetNeck',
in_channels=512,
num_deconv_filters=(256, 128, 64),
num_deconv_kernels=(4, 4, 4),
use_dcn=True),
bbox_head=dict(
type='CenterNetHead',
num_classes=80,
in_channels=64,
feat_channels=64,
loss_center_heatmap=dict(type='GaussianFocalLoss', loss_weight=1.0),
loss_wh=dict(type='L1Loss', loss_weight=0.1),
loss_offset=dict(type='L1Loss', loss_weight=1.0)),
train_cfg=None,
test_cfg=dict(topk=100, local_maximum_kernel=3, max_per_img=100))
train_pipeline = [
dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(
type='RandomCenterCropPad',
# The cropped images are padded into squares during training,
# but may be less than crop_size.
crop_size=(512, 512),
ratios=(0.6, 0.7, 0.8, 0.9, 1.0, 1.1, 1.2, 1.3),
mean=[0, 0, 0],
std=[1, 1, 1],
to_rgb=True,
test_pad_mode=None),
# Make sure the output is always crop_size.
dict(type='Resize', scale=(512, 512), keep_ratio=True),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs')
]
test_pipeline = [
dict(
type='LoadImageFromFile',
backend_args={{_base_.backend_args}},
to_float32=True),
# don't need Resize
dict(
type='RandomCenterCropPad',
ratios=None,
border=None,
mean=[0, 0, 0],
std=[1, 1, 1],
to_rgb=True,
test_mode=True,
test_pad_mode=['logical_or', 31],
test_pad_add_pix=1),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'border'))
]
# Use RepeatDataset to speed up training
train_dataloader = dict(
batch_size=16,
num_workers=4,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
_delete_=True,
type='RepeatDataset',
times=5,
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={{_base_.backend_args}},
)))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = val_dataloader
# optimizer
# Based on the default settings of modern detectors, the SGD effect is better
# than the Adam in the source code, so we use SGD default settings and
# if you use adam+lr5e-4, the map is 29.1.
optim_wrapper = dict(clip_grad=dict(max_norm=35, norm_type=2))
max_epochs = 28
# learning policy
# Based on the default settings of modern detectors, we added warmup settings.
param_scheduler = [
dict(
type='LinearLR', start_factor=0.001, by_epoch=False, begin=0,
end=1000),
dict(
type='MultiStepLR',
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[18, 24], # the real step is [18*5, 24*5]
gamma=0.1)
]
train_cfg = dict(max_epochs=max_epochs) # the real epoch is 28*5=140
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (16 samples per GPU)
auto_scale_lr = dict(base_batch_size=128)
mmde/mmdet/.mim/configs/centernet/centernet_r18_8xb16-crop512-140e_coco.py 0 → 100644
View file @ eb1107e4
_base_ = './centernet_r18-dcnv2_8xb16-crop512-140e_coco.py'
model = dict(neck=dict(use_dcn=False))
mmde/mmdet/.mim/configs/centernet/centernet_tta.py 0 → 100644
View file @ eb1107e4
# This is different from the TTA of official CenterNet.
tta_model = dict(
type='DetTTAModel',
tta_cfg=dict(nms=dict(type='nms', iou_threshold=0.5), max_per_img=100))
tta_pipeline = [
dict(type='LoadImageFromFile', to_float32=True, backend_args=None),
dict(
type='TestTimeAug',
transforms=[
[
# ``RandomFlip`` must be placed before ``RandomCenterCropPad``,
# otherwise bounding box coordinates after flipping cannot be
# recovered correctly.
dict(type='RandomFlip', prob=1.),
dict(type='RandomFlip', prob=0.)
],
[
dict(
type='RandomCenterCropPad',
ratios=None,
border=None,
mean=[0, 0, 0],
std=[1, 1, 1],
to_rgb=True,
test_mode=True,
test_pad_mode=['logical_or', 31],
test_pad_add_pix=1),
],
[dict(type='LoadAnnotations', with_bbox=True)],
[
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'flip', 'flip_direction', 'border'))
]
])
]
mmde/mmdet/.mim/configs/centernet/metafile.yml 0 → 100644
View file @ eb1107e4
Collections:
- Name: CenterNet
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x TITANXP GPUs
Architecture:
- ResNet
Paper:
URL: https://arxiv.org/abs/1904.07850
Title: 'Objects as Points'
README: configs/centernet/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.13.0/mmdet/models/detectors/centernet.py#L10
Version: v2.13.0
Models:
- Name: centernet_r18-dcnv2_8xb16-crop512-140e_coco
In Collection: CenterNet
Config: configs/centernet/centernet_r18-dcnv2_8xb16-crop512-140e_coco.py
Metadata:
Batch Size: 128
Training Memory (GB): 3.47
Epochs: 140
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 29.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_dcnv2_140e_coco/centernet_resnet18_dcnv2_140e_coco_20210702_155131-c8cd631f.pth
- Name: centernet_r18_8xb16-crop512-140e_coco
In Collection: CenterNet
Config: configs/centernet/centernet_r18_8xb16-crop512-140e_coco.py
Metadata:
Batch Size: 128
Training Memory (GB): 3.45
Epochs: 140
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 25.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/centernet/centernet_resnet18_140e_coco/centernet_resnet18_140e_coco_20210705_093630-bb5b3bf7.pth
- Name: centernet-update_r50-caffe_fpn_ms-1x_coco
In Collection: CenterNet
Config: configs/centernet/centernet-update_r50-caffe_fpn_ms-1x_coco.py
Metadata:
Batch Size: 16
Training Memory (GB): 3.3
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.2
Weights: https://download.openmmlab.com/mmdetection/v3.0/centernet/centernet-update_r50-caffe_fpn_ms-1x_coco/centernet-update_r50-caffe_fpn_ms-1x_coco_20230512_203845-8306baf2.pth
mmde/mmdet/.mim/configs/centripetalnet/centripetalnet_hourglass104_16xb6-crop511-210e-mstest_coco.py 0 → 100644
View file @ eb1107e4
_base_ = [
'../_base_/default_runtime.py', '../_base_/datasets/coco_detection.py'
]
data_preprocessor = dict(
type='DetDataPreprocessor',
mean=[123.675, 116.28, 103.53],
std=[58.395, 57.12, 57.375],
bgr_to_rgb=True)
# model settings
model = dict(
type='CornerNet',
data_preprocessor=data_preprocessor,
backbone=dict(
type='HourglassNet',
downsample_times=5,
num_stacks=2,
stage_channels=[256, 256, 384, 384, 384, 512],
stage_blocks=[2, 2, 2, 2, 2, 4],
norm_cfg=dict(type='BN', requires_grad=True)),
neck=None,
bbox_head=dict(
type='CentripetalHead',
num_classes=80,
in_channels=256,
num_feat_levels=2,
corner_emb_channels=0,
loss_heatmap=dict(
type='GaussianFocalLoss', alpha=2.0, gamma=4.0, loss_weight=1),
loss_offset=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1),
loss_guiding_shift=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=0.05),
loss_centripetal_shift=dict(
type='SmoothL1Loss', beta=1.0, loss_weight=1)),
# training and testing settings
train_cfg=None,
test_cfg=dict(
corner_topk=100,
local_maximum_kernel=3,
distance_threshold=0.5,
score_thr=0.05,
max_per_img=100,
nms=dict(type='soft_nms', iou_threshold=0.5, method='gaussian')))
# data settings
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=_base_.backend_args),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PhotoMetricDistortion',
brightness_delta=32,
contrast_range=(0.5, 1.5),
saturation_range=(0.5, 1.5),
hue_delta=18),
dict(
# The cropped images are padded into squares during training,
# but may be smaller than crop_size.
type='RandomCenterCropPad',
crop_size=(511, 511),
ratios=(0.6, 0.7, 0.8, 0.9, 1.0, 1.1, 1.2, 1.3),
test_mode=False,
test_pad_mode=None,
mean=data_preprocessor['mean'],
std=data_preprocessor['std'],
# Image data is not converted to rgb.
to_rgb=data_preprocessor['bgr_to_rgb']),
dict(type='Resize', scale=(511, 511), keep_ratio=False),
dict(type='RandomFlip', prob=0.5),
dict(type='PackDetInputs'),
]
test_pipeline = [
dict(
type='LoadImageFromFile',
to_float32=True,
backend_args=_base_.backend_args),
# don't need Resize
dict(
type='RandomCenterCropPad',
crop_size=None,
ratios=None,
border=None,
test_mode=True,
test_pad_mode=['logical_or', 127],
mean=data_preprocessor['mean'],
std=data_preprocessor['std'],
# Image data is not converted to rgb.
to_rgb=data_preprocessor['bgr_to_rgb']),
dict(type='LoadAnnotations', with_bbox=True),
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'border'))
]
train_dataloader = dict(
batch_size=6,
num_workers=3,
batch_sampler=None,
dataset=dict(pipeline=train_pipeline))
val_dataloader = dict(dataset=dict(pipeline=test_pipeline))
test_dataloader = val_dataloader
# optimizer
optim_wrapper = dict(
type='OptimWrapper',
optimizer=dict(type='Adam', lr=0.0005),
clip_grad=dict(max_norm=35, norm_type=2))
max_epochs = 210
# learning rate
param_scheduler = [
dict(
type='LinearLR',
start_factor=1.0 / 3,
by_epoch=False,
begin=0,
end=500),
dict(
type='MultiStepLR',
begin=0,
end=max_epochs,
by_epoch=True,
milestones=[190],
gamma=0.1)
]
train_cfg = dict(
type='EpochBasedTrainLoop', max_epochs=max_epochs, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (16 GPUs) x (6 samples per GPU)
auto_scale_lr = dict(base_batch_size=96)
tta_model = dict(
type='DetTTAModel',
tta_cfg=dict(
nms=dict(type='soft_nms', iou_threshold=0.5, method='gaussian'),
max_per_img=100))
tta_pipeline = [
dict(
type='LoadImageFromFile',
to_float32=True,
backend_args=_base_.backend_args),
dict(
type='TestTimeAug',
transforms=[
[
# ``RandomFlip`` must be placed before ``RandomCenterCropPad``,
# otherwise bounding box coordinates after flipping cannot be
# recovered correctly.
dict(type='RandomFlip', prob=1.),
dict(type='RandomFlip', prob=0.)
],
[
dict(
type='RandomCenterCropPad',
crop_size=None,
ratios=None,
border=None,
test_mode=True,
test_pad_mode=['logical_or', 127],
mean=data_preprocessor['mean'],
std=data_preprocessor['std'],
# Image data is not converted to rgb.
to_rgb=data_preprocessor['bgr_to_rgb'])
],
[dict(type='LoadAnnotations', with_bbox=True)],
[
dict(
type='PackDetInputs',
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
'flip', 'flip_direction', 'border'))
]
])
]
mmde/mmdet/.mim/configs/centripetalnet/metafile.yml 0 → 100644
View file @ eb1107e4
Collections:
- Name: CentripetalNet
Metadata:
Training Data: COCO
Training Techniques:
- Adam
Training Resources: 16x V100 GPUs
Architecture:
- Corner Pooling
- Stacked Hourglass Network
Paper:
URL: https://arxiv.org/abs/2003.09119
Title: 'CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection'
README: configs/centripetalnet/README.md
Code:
URL: https://github.com/open-mmlab/mmdetection/blob/v2.5.0/mmdet/models/detectors/cornernet.py#L9
Version: v2.5.0
Models:
- Name: centripetalnet_hourglass104_16xb6-crop511-210e-mstest_coco
In Collection: CentripetalNet
Config: configs/centripetalnet/centripetalnet_hourglass104_16xb6-crop511-210e-mstest_coco.py
Metadata:
Batch Size: 96
Training Memory (GB): 16.7
inference time (ms/im):
- value: 270.27
hardware: V100
backend: PyTorch
batch size: 1
mode: FP32
resolution: (800, 1333)
Epochs: 210
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 44.8
Weights: https://download.openmmlab.com/mmdetection/v2.0/centripetalnet/centripetalnet_hourglass104_mstest_16x6_210e_coco/centripetalnet_hourglass104_mstest_16x6_210e_coco_20200915_204804-3ccc61e5.pth
mmde/mmdet/.mim/configs/cityscapes/faster-rcnn_r50_fpn_1x_cityscapes.py 0 → 100644
View file @ eb1107e4
_base_ = [
'../_base_/models/faster-rcnn_r50_fpn.py',
'../_base_/datasets/cityscapes_detection.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_1x.py'
]
model = dict(
backbone=dict(init_cfg=None),
roi_head=dict(
bbox_head=dict(
num_classes=8,
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))))
# optimizer
# lr is set for a batch size of 8
optim_wrapper = dict(optimizer=dict(lr=0.01))
# learning rate
param_scheduler = [
dict(
type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
dict(
type='MultiStepLR',
begin=0,
end=8,
by_epoch=True,
# [7] yields higher performance than [6]
milestones=[7],
gamma=0.1)
]
# actual epoch = 8 * 8 = 64
train_cfg = dict(max_epochs=8)
# For better, more stable performance initialize from COCO
load_from = 'https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth' # noqa
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (1 samples per GPU)
# TODO: support auto scaling lr
# auto_scale_lr = dict(base_batch_size=8)
mmde/mmdet/.mim/configs/cityscapes/mask-rcnn_r50_fpn_1x_cityscapes.py 0 → 100644
View file @ eb1107e4
_base_ = [
'../_base_/models/mask-rcnn_r50_fpn.py',
'../_base_/datasets/cityscapes_instance.py',
'../_base_/default_runtime.py', '../_base_/schedules/schedule_1x.py'
]
model = dict(
backbone=dict(init_cfg=None),
roi_head=dict(
bbox_head=dict(
type='Shared2FCBBoxHead',
num_classes=8,
loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)),
mask_head=dict(num_classes=8)))
# optimizer
# lr is set for a batch size of 8
optim_wrapper = dict(optimizer=dict(lr=0.01))
# learning rate
param_scheduler = [
dict(
type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
dict(
type='MultiStepLR',
begin=0,
end=8,
by_epoch=True,
# [7] yields higher performance than [6]
milestones=[7],
gamma=0.1)
]
# actual epoch = 8 * 8 = 64
train_cfg = dict(max_epochs=8)
# For better, more stable performance initialize from COCO
load_from = 'https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth' # noqa
# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (1 samples per GPU)
# TODO: support auto scaling lr
# auto_scale_lr = dict(base_batch_size=8)
mmde/mmdet/.mim/configs/common/lsj-100e_coco-detection.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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
train_pipeline = [
dict(type='LoadImageFromFile', backend_args=backend_args),
dict(type='LoadAnnotations', with_bbox=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',
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 = 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)
mmde/mmdet/.mim/configs/common/lsj-100e_coco-instance.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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
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 = 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)
mmde/mmdet/.mim/configs/common/lsj-200e_coco-detection.py 0 → 100644
View file @ eb1107e4
_base_ = './lsj-100e_coco-detection.py'
# 8x25=200e
train_dataloader = 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)
]
mmde/mmdet/.mim/configs/common/lsj-200e_coco-instance.py 0 → 100644
View file @ eb1107e4
_base_ = './lsj-100e_coco-instance.py'
# 8x25=200e
train_dataloader = 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)
]
mmde/mmdet/.mim/configs/common/ms-90k_coco.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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 = 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 = 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 = 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 = dict(
type='IterBasedTrainLoop', max_iters=max_iter, val_interval=10000)
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=1000),
dict(
type='MultiStepLR',
begin=0,
end=max_iter,
by_epoch=False,
milestones=[60000, 80000],
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)
default_hooks = dict(checkpoint=dict(by_epoch=False, interval=10000))
log_processor = dict(by_epoch=False)
mmde/mmdet/.mim/configs/common/ms-poly-90k_coco-instance.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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 = 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 = 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 = 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 = dict(
type='IterBasedTrainLoop', max_iters=max_iter, val_interval=10000)
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=1000),
dict(
type='MultiStepLR',
begin=0,
end=max_iter,
by_epoch=False,
milestones=[60000, 80000],
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)
default_hooks = dict(checkpoint=dict(by_epoch=False, interval=10000))
log_processor = dict(by_epoch=False)
mmde/mmdet/.mim/configs/common/ms-poly_3x_coco-instance.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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 = 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 = dict(
batch_size=2,
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'],
backend_args=backend_args)
test_evaluator = val_evaluator
# training schedule for 3x with `RepeatDataset`
train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=12, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning rate
# Experiments show that using milestones=[9, 11] has higher performance
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=[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)
mmde/mmdet/.mim/configs/common/ms_3x_coco-instance.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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 = 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 = 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_epochs=12, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning rate
# Experiments show that using milestones=[9, 11] has higher performance
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=[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)
mmde/mmdet/.mim/configs/common/ms_3x_coco.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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),
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,
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_epochs=12, val_interval=1)
val_cfg = dict(type='ValLoop')
test_cfg = dict(type='TestLoop')
# learning rate
# Experiments show that using milestones=[9, 11] has higher performance
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=[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)
mmde/mmdet/.mim/configs/common/ssj_270k_coco-instance.py 0 → 100644
View file @ eb1107e4
_base_ = '../_base_/default_runtime.py'
# 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.
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 = 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 = 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
# The model is trained by 270k iterations with batch_size 64,
# which is roughly equivalent to 144 epochs.
max_iters = 270000
train_cfg = dict(
type='IterBasedTrainLoop', max_iters=max_iters, val_interval=10000)
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 policy
# lr steps at [0.9, 0.95, 0.975] of the maximum iterations
param_scheduler = [
dict(
type='LinearLR', start_factor=0.001, by_epoch=False, begin=0,
end=1000),
dict(
type='MultiStepLR',
begin=0,
end=270000,
by_epoch=False,
milestones=[243000, 256500, 263250],
gamma=0.1)
]
default_hooks = dict(checkpoint=dict(by_epoch=False, interval=10000))
log_processor = dict(by_epoch=False)
# 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)
mmde/mmdet/.mim/configs/common/ssj_scp_270k_coco-instance.py 0 → 100644
View file @ eb1107e4
_base_ = 'ssj_270k_coco-instance.py'
# 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 = dict(
dataset=dict(
_delete_=True,
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