| 12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485 |
- _base_ = '../common/ms-poly-90k_coco-instance.py'
- # model settings
- model = dict(
- type='CondInst',
- data_preprocessor=dict(
- type='DetDataPreprocessor',
- mean=[123.675, 116.28, 103.53],
- std=[58.395, 57.12, 57.375],
- bgr_to_rgb=True,
- pad_mask=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,
- init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50'),
- style='pytorch'),
- neck=dict(
- type='FPN',
- in_channels=[256, 512, 1024, 2048],
- out_channels=256,
- start_level=1,
- add_extra_convs='on_output', # use P5
- num_outs=5,
- relu_before_extra_convs=True),
- bbox_head=dict(
- type='CondInstBboxHead',
- num_params=169,
- num_classes=80,
- in_channels=256,
- stacked_convs=4,
- feat_channels=256,
- strides=[8, 16, 32, 64, 128],
- norm_on_bbox=True,
- centerness_on_reg=True,
- dcn_on_last_conv=False,
- center_sampling=True,
- conv_bias=True,
- loss_cls=dict(
- type='FocalLoss',
- use_sigmoid=True,
- gamma=2.0,
- alpha=0.25,
- loss_weight=1.0),
- loss_bbox=dict(type='GIoULoss', loss_weight=1.0),
- loss_centerness=dict(
- type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0)),
- mask_head=dict(
- type='CondInstMaskHead',
- num_layers=3,
- feat_channels=8,
- size_of_interest=8,
- mask_out_stride=4,
- max_masks_to_train=300,
- mask_feature_head=dict(
- in_channels=256,
- feat_channels=128,
- start_level=0,
- end_level=2,
- out_channels=8,
- mask_stride=8,
- num_stacked_convs=4,
- norm_cfg=dict(type='BN', requires_grad=True)),
- loss_mask=dict(
- type='DiceLoss',
- use_sigmoid=True,
- activate=True,
- eps=5e-6,
- loss_weight=1.0)),
- # model training and testing settings
- test_cfg=dict(
- nms_pre=1000,
- min_bbox_size=0,
- score_thr=0.05,
- nms=dict(type='nms', iou_threshold=0.6),
- max_per_img=100,
- mask_thr=0.5))
- # optimizer
- optim_wrapper = dict(optimizer=dict(lr=0.01))
|
