mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1.py

_base_ = [
    '../_base_/models/mask_rcnn_r50_fpn.py',
    '../_base_/datasets/coco_instance.py',
    '../_base_/schedules/schedule_2x.py', '../_base_/default_runtime.py'
]
model = dict(
    roi_head=dict(
        bbox_head=dict(
            num_classes=1203,
            cls_predictor_cfg=dict(type='NormedLinear', tempearture=20),
            loss_cls=dict(
                type='SeesawLoss',
                p=0.8,
                q=2.0,
                num_classes=1203,
                loss_weight=1.0)),
        mask_head=dict(num_classes=1203)),
    test_cfg=dict(
        rcnn=dict(
            score_thr=0.0001,
            # LVIS allows up to 300
            max_per_img=300)))
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=[(1333, 640), (1333, 672), (1333, 704), (1333, 736),
                   (1333, 768), (1333, 800)],
        multiscale_mode='value',
        keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    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=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]
dataset_type = 'LVISV1Dataset'
data_root = 'data/lvis_v1/'
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/lvis_v1_train.json',
        img_prefix=data_root,
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/lvis_v1_val.json',
        img_prefix=data_root,
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/lvis_v1_val.json',
        img_prefix=data_root,
        pipeline=test_pipeline))
evaluation = dict(interval=24, metric=['bbox', 'segm'])