|
- model = dict(
- type='CascadeRCNN',
- pretrained='torchvision://resnet50',
- 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'),
- 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, 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=0.1111111111111111, 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', out_size=7, sample_num=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=2,
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[0.0, 0.0, 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=2,
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[0.0, 0.0, 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=2,
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- target_means=[0.0, 0.0, 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))
- ]))
- 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_across_levels=False,
- nms_pre=2000,
- nms_post=2000,
- max_num=2000,
- nms_thr=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_across_levels=False,
- nms_pre=1000,
- nms_post=1000,
- max_num=1000,
- nms_thr=0.7,
- min_bbox_size=0),
- rcnn=dict(
- score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
- dataset_type = 'CocoDataset'
- data_root = '/share/chenbo/Dataset/Adullt_children/Dataset/'
- classes = ('student', 'adult')
- img_norm_cfg = dict(
- mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
- train_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(type='Resize', img_scale=[(1333, 640), (1333, 960)], keep_ratio=True),
- dict(type='RandomFlip', flip_ratio=0.5),
- dict(
- type='Normalize',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- to_rgb=True),
- dict(type='Pad', size_divisor=32),
- dict(type='DefaultFormatBundle'),
- dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
- ]
- test_pipeline = [
- dict(type='LoadImageFromFile'),
- dict(
- type='MultiScaleFlipAug',
- img_scale=(1333, 800),
- flip=False,
- transforms=[
- dict(type='Resize', keep_ratio=True),
- dict(type='RandomFlip'),
- dict(
- type='Normalize',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- to_rgb=True),
- 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='CocoDataset',
- classes=('student', 'adult'),
- ann_file=
- '/share/chenbo/Dataset/Adullt_children/Dataset/annotations/train_data_0706.json',
- img_prefix=
- '/share/chenbo/Dataset/Adullt_children/Dataset/imgs/0706_train',
- pipeline=[
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='Resize',
- img_scale=[(1333, 640), (1333, 960)],
- keep_ratio=True),
- dict(type='RandomFlip', flip_ratio=0.5),
- dict(
- type='Normalize',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- to_rgb=True),
- dict(type='Pad', size_divisor=32),
- dict(type='DefaultFormatBundle'),
- dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
- ]),
- dict(
- type='CocoDataset',
- classes=('student', 'adult'),
- ann_file=
- '/share/chenbo/Dataset/Adullt_children/Dataset/annotations/train_data_0717.json',
- img_prefix=
- '/share/chenbo/Dataset/Adullt_children/frames/0714_shuangshi_train_model_selection',
- pipeline=[
- dict(type='LoadImageFromFile'),
- dict(type='LoadAnnotations', with_bbox=True),
- dict(
- type='Resize',
- img_scale=[(1333, 640), (1333, 960)],
- keep_ratio=True),
- dict(type='RandomFlip', flip_ratio=0.5),
- dict(
- type='Normalize',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- to_rgb=True),
- dict(type='Pad', size_divisor=32),
- dict(type='DefaultFormatBundle'),
- dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
- ])
- ],
- val=dict(
- type='CocoDataset',
- classes=('student', 'adult'),
- ann_file=
- '/share/chenbo/Dataset/Adullt_children/Dataset/annotations/test_data_0713.json',
- img_prefix=
- '/share/chenbo/Dataset/Adullt_children/frames/0707_shuangshi_test_frames_new',
- pipeline=[
- dict(type='LoadImageFromFile'),
- dict(
- type='MultiScaleFlipAug',
- img_scale=(1333, 800),
- flip=False,
- transforms=[
- dict(type='Resize', keep_ratio=True),
- dict(type='RandomFlip'),
- dict(
- type='Normalize',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- to_rgb=True),
- dict(type='Pad', size_divisor=32),
- dict(type='ImageToTensor', keys=['img']),
- dict(type='Collect', keys=['img'])
- ])
- ]),
- test=dict(
- type='CocoDataset',
- classes=('student', 'adult'),
- ann_file=
- '/share/chenbo/Dataset/Adullt_children/Dataset/annotations/val_data_0706.json',
- img_prefix=
- '/share/chenbo/Dataset/Adullt_children/frames/0707_shuangshi_test_frames_new',
- pipeline=[
- dict(type='LoadImageFromFile'),
- dict(
- type='MultiScaleFlipAug',
- img_scale=(1333, 800),
- flip=False,
- transforms=[
- dict(type='Resize', keep_ratio=True),
- dict(type='RandomFlip'),
- dict(
- type='Normalize',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- to_rgb=True),
- dict(type='Pad', size_divisor=32),
- dict(type='ImageToTensor', keys=['img']),
- dict(type='Collect', keys=['img'])
- ])
- ]))
- evaluation = dict(interval=5, metric='bbox')
- optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
- optimizer_config = dict(grad_clip=None)
- lr_config = dict(
- policy='step',
- warmup='linear',
- warmup_iters=500,
- warmup_ratio=0.001,
- step=[8, 11])
- total_epochs = 12
- checkpoint_config = dict(interval=1)
- log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
- dist_params = dict(backend='nccl')
- log_level = 'INFO'
- load_from = '/workspace/PX/adult_children_recognition/mmdetection/pretrained/cascade_rcnn_r50_fpn_1x_coco_20200316-3dc56deb.pth'
- resume_from = None
- workflow = [('train', 1)]
- no_validate = True
- work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x_student'
- gpu_ids = range(0, 1)
|