| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101 |
- _base_ = [
- '../_base_/datasets/coco_detection.py',
- '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
- ]
- num_stages = 6
- num_proposals = 100
- model = dict(
- type='SparseRCNN',
- 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),
- 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=0,
- add_extra_convs='on_input',
- num_outs=4),
- rpn_head=dict(
- type='EmbeddingRPNHead',
- num_proposals=num_proposals,
- proposal_feature_channel=256),
- roi_head=dict(
- type='SparseRoIHead',
- num_stages=num_stages,
- stage_loss_weights=[1] * num_stages,
- proposal_feature_channel=256,
- bbox_roi_extractor=dict(
- type='SingleRoIExtractor',
- roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=2),
- out_channels=256,
- featmap_strides=[4, 8, 16, 32]),
- bbox_head=[
- dict(
- type='DIIHead',
- num_classes=80,
- num_ffn_fcs=2,
- num_heads=8,
- num_cls_fcs=1,
- num_reg_fcs=3,
- feedforward_channels=2048,
- in_channels=256,
- dropout=0.0,
- ffn_act_cfg=dict(type='ReLU', inplace=True),
- dynamic_conv_cfg=dict(
- type='DynamicConv',
- in_channels=256,
- feat_channels=64,
- out_channels=256,
- input_feat_shape=7,
- act_cfg=dict(type='ReLU', inplace=True),
- norm_cfg=dict(type='LN')),
- loss_bbox=dict(type='L1Loss', loss_weight=5.0),
- loss_iou=dict(type='GIoULoss', loss_weight=2.0),
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=2.0),
- bbox_coder=dict(
- type='DeltaXYWHBBoxCoder',
- clip_border=False,
- target_means=[0., 0., 0., 0.],
- target_stds=[0.5, 0.5, 1., 1.])) for _ in range(num_stages)
- ]),
- # training and testing settings
- train_cfg=dict(
- rpn=None,
- rcnn=[
- dict(
- assigner=dict(
- type='HungarianAssigner',
- match_costs=[
- dict(type='FocalLossCost', weight=2.0),
- dict(type='BBoxL1Cost', weight=5.0, box_format='xyxy'),
- dict(type='IoUCost', iou_mode='giou', weight=2.0)
- ]),
- sampler=dict(type='PseudoSampler'),
- pos_weight=1) for _ in range(num_stages)
- ]),
- test_cfg=dict(rpn=None, rcnn=dict(max_per_img=num_proposals)))
- # optimizer
- optim_wrapper = dict(
- optimizer=dict(
- _delete_=True, type='AdamW', lr=0.000025, weight_decay=0.0001),
- clip_grad=dict(max_norm=1, norm_type=2))
|
