dataset_type = 'CocoDataset'
data_root = '/dataset/coco/'
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, with_mask=True),
    dict(
        type='Resize',
        img_scale=[(768, 512), (768, 480), (768, 448), (768, 416), (768, 384),
                   (768, 352)],
#         img_scale=[(512, 512), (512, 480), (512, 448), (512, 416), (512, 384),
#                    (512, 352)],
        multiscale_mode='value',
        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', 'gt_masks'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(768, 448),
        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=6,#8
    workers_per_gpu=6,
    train=dict(
        type='CocoDataset',
        # ann_file='/data/person_data/data_cocotrainval_matting_1_2_3_dataset2000_tal11315_data4000_tal9052_PM850_pic2018_2021_supervisely_light.json.json',
        ann_file = '/data/person_data/data_cocotrainval_matting_1_2_3_dataset2000_tal11315_data4000_tal9052_PM850_pic2018_2021_light.json',
        img_prefix='/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
            dict(
                type='Resize',
                img_scale=[(768, 512), (768, 480), (768, 448), (768, 416), (768, 384),
                   (768, 352)],
#               img_scale=[(512, 512), (512, 480), (512, 448), (512, 416), (512, 384),
#                    (512, 352)],
                multiscale_mode='value',
                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', 'gt_masks'])
        ]),
    val=dict(
        type='CocoDataset',
        ann_file='/data/person_data/model_test_portrait/model_test_portrait_1.json',
        img_prefix='/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(768, 448),
                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',
        # ann_file='/data/person_data/model_test_portrait_1.json',
        ann_file='/data/person_data/model_test_pic2021.json',
        img_prefix='/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(768, 448),
                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(metric=['bbox', 'segm'])
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.3333333333333333,
    step=[20, 25, 31] #[27, 33]
)
runner = dict(type='EpochBasedRunner', max_epochs=36)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
opencv_num_threads = 0
mp_start_method = 'fork'
auto_scale_lr = dict(enable=False, base_batch_size=16)
model = dict(
    type='SOLOv2',
    backbone=dict(
        type='ResNet',
        depth=101,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        init_cfg=dict(type='Pretrained', 
                      #checkpoint='torchvision://resnet101'
                      checkpoint='resnet101-5d3b4d8f.pth'
                     ),
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=8,
        start_level=0,
        num_outs=5),
    mask_head=dict(
        type='SOLOV2Head',
        num_classes=1,#80
        in_channels=8,
        feat_channels=32,# can not modify
        stacked_convs=4,
        strides=[8, 8, 16, 32, 32],
        scale_ranges=((1, 56), (28, 112), (56, 224), (112, 448), (224, 896)),#((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,
        mask_feature_head=dict(
            feat_channels=8,
            start_level=0,
            end_level=3,
            out_channels=8,
            mask_stride=4,
            norm_cfg=dict(type='GN', num_groups=8, requires_grad=True)),#32,16
        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)),
    test_cfg=dict(
        nms_pre=500,
        score_thr=0.1,
        mask_thr=0.5,
        filter_thr=0.05,
        kernel='gaussian',
        sigma=2.0,
        max_per_img=100))
work_dir = './work_dirs/solov2_r101_3x_c8_twoc_test'
auto_resume = False
gpu_ids = [0]