search

TianwenZhang0825 / LS-SSDD-v1.0-OPEN

This is a Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) from Sentinel-1, for small ship detec-tion under large-scale backgrounds. LS-SSDD-v1.0 contains 15 large-scale SAR images whose ground truths are correctly labeled by SAR experts by drawing support from Automatic Identifica-tion System (AIS) and Google Earth. To facilitate network training, the large-scale images are directly cut into 9,000 sub-images without bells and whistles, providing convenience for subsequent detec-tion result presentation in large-scale SAR images.
Apache License 2.0
64 stars 11 forks source link

Can the author provide more network details of MMDetection configuration file? #3

Open Mio2020 opened 3 years ago

Mio2020 commented 3 years ago 
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 commented 5 months ago

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