Can the author provide more network details of MMDetection configuration file?

[Mio2020]

model = dict(
    type='FasterRCNN',
    pretrained='torchvision://resnet50',
    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,
        style='pytorch'),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            scales=[8],
            ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[0.0, 0.0, 0.0, 0.0],
            target_stds=[1.0, 1.0, 1.0, 1.0]),
        loss_cls=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
    roi_head=dict(
        type='StandardRoIHead',
        bbox_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        bbox_head=dict(
            type='Shared2FCBBoxHead',
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            num_classes=1,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0.0, 0.0, 0.0, 0.0],
                target_stds=[0.1, 0.1, 0.2, 0.2]),
            reg_class_agnostic=False,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='L1Loss', loss_weight=1.0))))
train_cfg = dict(
    rpn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.7,
            neg_iou_thr=0.3,
            min_pos_iou=0.3,
            match_low_quality=True,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=256,
            pos_fraction=0.5,
            neg_pos_ub=-1,
            add_gt_as_proposals=False),
        allowed_border=-1,
        pos_weight=-1,
        debug=False),
    rpn_proposal=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=1000,
        max_num=1000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.5,
            min_pos_iou=0.5,
            match_low_quality=False,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=512,
            pos_fraction=0.25,
            neg_pos_ub=-1,
            add_gt_as_proposals=True),
        pos_weight=-1,
        debug=False))
test_cfg = dict(
    rpn=dict(
        nms_across_levels=False,
        nms_pre=1000,
        nms_post=1000,
        max_num=1000,
        nms_thr=0.5,
        min_bbox_size=0),
    rcnn=dict(
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.65),
        max_per_img=100))
dataset_type = 'VOCDataset'
data_root = 'data/'
img_norm_cfg = dict(
    mean=[78.934677, 78.934677, 78.934677],
    std=[57.484476, 57.484476, 57.484476],
    to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(type='Resize', img_scale=(800, 800), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[78.934677, 78.934677, 78.934677],
        std=[57.484476, 57.484476, 57.484476],
        to_rgb=True),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(800, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[78.934677, 78.934677, 78.934677],
                std=[57.484476, 57.484476, 57.484476],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=1,
    workers_per_gpu=1,
    train=dict(
        type='RepeatDataset',
        times=3,
        dataset=dict(
            type='VOCDataset',
            ann_file=['data/VOC2007_LSSSDD/ImageSets/Main/trainval.txt'],
            img_prefix=['data/VOC2007_LSSSDD/'],
            pipeline=[
                dict(type='LoadImageFromFile'),
                dict(type='LoadAnnotations', with_bbox=True),
                dict(type='Resize', img_scale=(800, 800), keep_ratio=True),
                dict(type='RandomFlip', flip_ratio=0.5),
                dict(
                    type='Normalize',
                    mean=[78.934677, 78.934677, 78.934677],
                    std=[57.484476, 57.484476, 57.484476],
                    to_rgb=True),
                dict(type='Pad', size_divisor=32),
                dict(type='DefaultFormatBundle'),
                dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
            ])),
    val=dict(
        type='VOCDataset',
        ann_file='data/VOC2007_LSSSDD/ImageSets/Main/test.txt',
        img_prefix='data/VOC2007_LSSSDD/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(800, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[78.934677, 78.934677, 78.934677],
                        std=[57.484476, 57.484476, 57.484476],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]),
    test=dict(
        type='VOCDataset',
        ann_file='data/VOC2007_LSSSDD/ImageSets/Main/test.txt',
        img_prefix='data/VOC2007_LSSSDD/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(800, 800),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[78.934677, 78.934677, 78.934677],
                        std=[57.484476, 57.484476, 57.484476],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]))
evaluation = dict(interval=1, metric='mAP')
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[8, 11])
total_epochs = 12
checkpoint_config = dict(interval=1, create_symlink=False)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
work_dir = './work_dirs\faster_rcnn_r50_fpn_1x_LSSSDD'
gpu_ids = range(0, 1)

This is my faster_rcnn_r50_fpn_1x_LSSSDD.py config file，got this result：

+-------+------+------+--------+-------+
| class | gts  | dets | recall | ap    |
+-------+------+------+--------+-------+
| ship  | 2378 | 2723 | 0.665  | 0.599 |
+-------+------+------+--------+-------+
| mAP   |      |      |        | 0.599 |
+-------+------+------+--------+-------+

If I change the anchor scale to 4:

anchor_generator=dict(
            type='AnchorGenerator',
            scales=[4],
            ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64]),

The AP got better but with many false alarm:

+-------+------+------+--------+-------+
| class | gts  | dets | recall | ap    |
+-------+------+------+--------+-------+
| ship  | 2378 | 5282 | 0.774  | 0.672 |
+-------+------+------+--------+-------+
| mAP   |      |      |        | 0.672 |
+-------+------+------+--------+-------+

There was a big difference between this result and the one in the paper. Increasing the training epoch doesn't work.

Could you tell me what's the problem with this config file? Thanks.

[hhanying]

Hi, have you been successful in resurfacing, please guide me, my MAP has been at 23%