1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586 |
- _base_ = [
- '../_base_/models/faster-rcnn_r50-caffe-c4.py',
- '../_base_/schedules/schedule_1x.py', '../_base_/datasets/voc0712.py',
- '../_base_/default_runtime.py'
- ]
- model = dict(roi_head=dict(bbox_head=dict(num_classes=20)))
- # dataset settings
- train_pipeline = [
- dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='RandomChoiceResize',
- scales=[(1333, 480), (1333, 512), (1333, 544), (1333, 576),
- (1333, 608), (1333, 640), (1333, 672), (1333, 704),
- (1333, 736), (1333, 768), (1333, 800)],
- keep_ratio=True),
- dict(type='RandomFlip', prob=0.5),
- dict(type='PackDetInputs')
- ]
- test_pipeline = [
- dict(type='LoadImageFromFile', backend_args={{_base_.backend_args}}),
- dict(type='Resize', scale=(1333, 800), keep_ratio=True),
- # avoid bboxes being resized
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='PackDetInputs',
- meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
- 'scale_factor'))
- ]
- train_dataloader = dict(
- sampler=dict(type='InfiniteSampler', shuffle=True),
- dataset=dict(
- _delete_=True,
- type='ConcatDataset',
- datasets=[
- dict(
- type='VOCDataset',
- data_root={{_base_.data_root}},
- ann_file='VOC2007/ImageSets/Main/trainval.txt',
- data_prefix=dict(sub_data_root='VOC2007/'),
- filter_cfg=dict(filter_empty_gt=True, min_size=32),
- pipeline=train_pipeline,
- backend_args={{_base_.backend_args}}),
- dict(
- type='VOCDataset',
- data_root={{_base_.data_root}},
- ann_file='VOC2012/ImageSets/Main/trainval.txt',
- data_prefix=dict(sub_data_root='VOC2012/'),
- 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
- # training schedule for 18k
- max_iter = 18000
- train_cfg = dict(
- _delete_=True,
- type='IterBasedTrainLoop',
- max_iters=max_iter,
- val_interval=3000)
- # learning rate
- param_scheduler = [
- dict(
- type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=100),
- dict(
- type='MultiStepLR',
- begin=0,
- end=max_iter,
- by_epoch=False,
- milestones=[12000, 16000],
- gamma=0.1)
- ]
- # optimizer
- optim_wrapper = dict(
- type='OptimWrapper',
- optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
- default_hooks = dict(checkpoint=dict(by_epoch=False, interval=3000))
- log_processor = dict(by_epoch=False)
|