mmdeploy/tests/test_codebase/test_mmrotate/data/model.py

# Copyright (c) OpenMMLab. All rights reserved.
dataset_type = 'DOTADataset'
data_root = 'tests/test_codebase/test_mmrotate/data/'
ann_file = 'dota_sample/'
file_client_args = dict(backend='disk')
val_pipeline = [
    dict(
        type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')),
    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
    dict(type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
    dict(type='ConvertBoxType', box_type_mapping=dict(gt_bboxes='rbox')),
    dict(
        type='mmdet.PackDetInputs',
        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                   'scale_factor'))
]
test_pipeline = [
    dict(
        type='mmdet.LoadImageFromFile', file_client_args=dict(backend='disk')),
    dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
    dict(
        type='mmdet.PackDetInputs',
        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                   'scale_factor'))
]
val_dataloader = dict(
    batch_size=1,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='DOTADataset',
        data_root=data_root,
        ann_file=ann_file,
        data_prefix=dict(img_path='trainval/images/'),
        test_mode=True,
        pipeline=[
            dict(
                type='mmdet.LoadImageFromFile',
                file_client_args=dict(backend='disk')),
            dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
            dict(
                type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
            dict(
                type='ConvertBoxType',
                box_type_mapping=dict(gt_bboxes='rbox')),
            dict(
                type='mmdet.PackDetInputs',
                meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                           'scale_factor'))
        ]))
test_dataloader = dict(
    batch_size=1,
    num_workers=2,
    persistent_workers=True,
    drop_last=False,
    sampler=dict(type='DefaultSampler', shuffle=False),
    dataset=dict(
        type='DOTADataset',
        data_root=data_root,
        ann_file=ann_file,
        data_prefix=dict(img_path='trainval/images/'),
        test_mode=True,
        pipeline=[
            dict(
                type='mmdet.LoadImageFromFile',
                file_client_args=dict(backend='disk')),
            dict(type='mmdet.Resize', scale=(1024, 1024), keep_ratio=True),
            dict(
                type='mmdet.LoadAnnotations', with_bbox=True, box_type='qbox'),
            dict(
                type='ConvertBoxType',
                box_type_mapping=dict(gt_bboxes='rbox')),
            dict(
                type='mmdet.PackDetInputs',
                meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                           'scale_factor'))
        ]))
default_scope = 'mmrotate'
vis_backends = [dict(type='LocalVisBackend')]
visualizer = dict(
    type='RotLocalVisualizer',
    vis_backends=[dict(type='LocalVisBackend')],
    name='visualizer')
model = dict(
    type='mmdet.RetinaNet',
    data_preprocessor=dict(
        type='mmdet.DetDataPreprocessor',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        bgr_to_rgb=True,
        pad_size_divisor=32,
        boxtype2tensor=False),
    backbone=dict(
        type='mmdet.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='mmdet.FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5),
    bbox_head=dict(
        type='mmdet.RetinaHead',
        num_classes=15,
        in_channels=256,
        stacked_convs=4,
        feat_channels=256,
        anchor_generator=dict(
            type='FakeRotatedAnchorGenerator',
            angle_version='le135',
            octave_base_scale=4,
            scales_per_octave=3,
            ratios=[1.0, 0.5, 2.0],
            strides=[8, 16, 32, 64, 128]),
        bbox_coder=dict(
            type='DeltaXYWHTRBBoxCoder',
            angle_version='le135',
            norm_factor=1,
            edge_swap=False,
            proj_xy=True,
            target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
            target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
        loss_cls=dict(
            type='mmdet.FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='mmdet.L1Loss', loss_weight=1.0)),
    train_cfg=dict(
        assigner=dict(
            type='mmdet.MaxIoUAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.4,
            min_pos_iou=0,
            ignore_iof_thr=-1,
            iou_calculator=dict(type='RBboxOverlaps2D')),
        sampler=dict(type='mmdet.PseudoSampler'),
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    test_cfg=dict(
        nms_pre=2000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(type='nms_rotated', iou_threshold=0.1),
        max_per_img=2000))