| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859 |
- _base_ = [
- '../_base_/models/mask-rcnn_r50_fpn.py',
- '../_base_/datasets/coco_instance.py',
- '../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py'
- ]
- model = dict(
- roi_head=dict(
- bbox_head=dict(
- num_classes=1203,
- cls_predictor_cfg=dict(type='NormedLinear', tempearture=20),
- loss_cls=dict(
- type='SeesawLoss',
- p=0.8,
- q=2.0,
- num_classes=1203,
- loss_weight=1.0)),
- mask_head=dict(num_classes=1203)),
- test_cfg=dict(
- rcnn=dict(
- score_thr=0.0001,
- # LVIS allows up to 300
- max_per_img=300)))
- # dataset settings
- train_pipeline = [
- dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
- dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
- dict(
- type='RandomChoiceResize',
- scales=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
- (1333, 768), (1333, 800)],
- keep_ratio=True),
- dict(type='RandomFlip', prob=0.5),
- dict(type='PackDetInputs')
- ]
- dataset_type = 'LVISV1Dataset'
- data_root = 'data/lvis_v1/'
- train_dataloader = dict(
- dataset=dict(
- type=dataset_type,
- data_root=data_root,
- ann_file='annotations/lvis_v1_train.json',
- data_prefix=dict(img=''),
- pipeline=train_pipeline))
- val_dataloader = dict(
- dataset=dict(
- type=dataset_type,
- data_root=data_root,
- ann_file='annotations/lvis_v1_val.json',
- data_prefix=dict(img='')))
- test_dataloader = val_dataloader
- val_evaluator = dict(
- type='LVISMetric',
- ann_file=data_root + 'annotations/lvis_v1_val.json',
- metric=['bbox', 'segm'])
- test_evaluator = val_evaluator
- train_cfg = dict(val_interval=24)
|
