mmdetection-2.26.0/configs/common/ssj_scp_270k_coco_instance.py

_base_ = '../_base_/default_runtime.py'
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
 mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
image_size = (1024, 1024)

file_client_args = dict(backend='disk')

# 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', file_client_args=file_client_args),
 dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
 dict(
 type='Resize',
 img_scale=image_size,
 ratio_range=(0.8, 1.25),
 multiscale_mode='range',
 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', flip_ratio=0.5),
 dict(type='Pad', size=image_size),
]
train_pipeline = [
 dict(type='CopyPaste', max_num_pasted=100),
 dict(type='Normalize', **img_norm_cfg),
 dict(type='DefaultFormatBundle'),
 dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
 dict(type='LoadImageFromFile', file_client_args=file_client_args),
 dict(
 type='MultiScaleFlipAug',
 img_scale=(1333, 800),
 flip=False,
 transforms=[
 dict(type='Resize', keep_ratio=True),
 dict(type='RandomFlip'),
 dict(type='Normalize', **img_norm_cfg),
 dict(type='Pad', size_divisor=32),
 dict(type='ImageToTensor', keys=['img']),
 dict(type='Collect', keys=['img']),
 ])
]

data = dict(
 samples_per_gpu=2,
 workers_per_gpu=2,
 train=dict(
 type='MultiImageMixDataset',
 dataset=dict(
 type=dataset_type,
 ann_file=data_root + 'annotations/instances_train2017.json',
 img_prefix=data_root + 'train2017/',
 pipeline=load_pipeline),
 pipeline=train_pipeline),
 val=dict(
 type=dataset_type,
 ann_file=data_root + 'annotations/instances_val2017.json',
 img_prefix=data_root + 'val2017/',
 pipeline=test_pipeline),
 test=dict(
 type=dataset_type,
 ann_file=data_root + 'annotations/instances_val2017.json',
 img_prefix=data_root + 'val2017/',
 pipeline=test_pipeline))

evaluation = dict(interval=6000, metric=['bbox', 'segm'])

# optimizer assumes batch_size = (32 GPUs) x (2 samples per GPU)
optimizer = dict(type='SGD', lr=0.1, momentum=0.9, weight_decay=0.00004)
optimizer_config = dict(grad_clip=None)

# lr steps at [0.9, 0.95, 0.975] of the maximum iterations
lr_config = dict(
 policy='step',
 warmup='linear',
 warmup_iters=1000,
 warmup_ratio=0.001,
 step=[243000, 256500, 263250])
checkpoint_config = dict(interval=6000)
# The model is trained by 270k iterations with batch_size 64,
# which is roughly equivalent to 144 epochs.
runner = dict(type='IterBasedRunner', max_iters=270000)

# 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)