solo_r50_fpn_1x_coco.py

_base_ = [
    '../_base_/datasets/coco_instance.py',
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
# model settings
model = dict(
    type='SOLO',
    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,
        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=0,
        num_outs=5),
    mask_head=dict(
        type='SOLOHead',
        num_classes=80,
        in_channels=256,
        stacked_convs=7,
        feat_channels=256,
        strides=[8, 8, 16, 32, 32],
        scale_ranges=((1, 96), (48, 192), (96, 384), (192, 768), (384, 2048)),
        pos_scale=0.2,
        num_grids=[40, 36, 24, 16, 12],
        cls_down_index=0,
        loss_mask=dict(type='DiceLoss', use_sigmoid=True, loss_weight=3.0),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        norm_cfg=dict(type='GN', num_groups=32, requires_grad=True)),
    # model training and testing settings
    test_cfg=dict(
        nms_pre=500,
        score_thr=0.1,
        mask_thr=0.5,
        filter_thr=0.05,
        kernel='gaussian',  # gaussian/linear
        sigma=2.0,
        max_per_img=100))

# optimizer
optim_wrapper = dict(optimizer=dict(lr=0.01))

val_evaluator = dict(metric='segm')
test_evaluator = val_evaluator