search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.74k stars 9.48k forks source link

Weird result in trained model inference: multiple detect on one object #6254

Closed accforaus closed 3 years ago

accforaus commented 3 years ago

Hi guys, I have some questions about the result in object detection.

I trained the model using custom coco datasets. and when I try inference,

it showed weird results like this: 스크린샷 2021-10-11 오전 9 37 12

This image using at training, I expected that objects in the image must have one label. But it showed multiple labels.

Here is the model configuration:


model = dict(
    type='MaskRCNN',
    pretrained=None,
    backbone=dict(
        type='SwinTransformer',
        embed_dim=96,
        depths=[2, 2, 6, 2],
        num_heads=[3, 6, 12, 24],
        window_size=7,
        mlp_ratio=4.0,
        qkv_bias=True,
        qk_scale=None,
        drop_rate=0.0,
        attn_drop_rate=0.0,
        drop_path_rate=0.1,
        ape=False,
        patch_norm=True,
        out_indices=(0, 1, 2, 3),
        use_checkpoint=False),
    neck=dict(
        type='FPN',
        in_channels=[96, 192, 384, 768],
        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=4,
            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)),
        mask_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        mask_head=dict(
            type='FCNMaskHead',
            num_convs=4,
            in_channels=256,
            conv_out_channels=256,
            num_classes=4,
            loss_mask=dict(
                type='CrossEntropyLoss', use_mask=True, 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_pre=2000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=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=True,
                ignore_iof_thr=-1),
            sampler=dict(
                type='RandomSampler',
                num=512,
                pos_fraction=0.25,
                neg_pos_ub=-1,
                add_gt_as_proposals=True),
            mask_size=28,
            pos_weight=-1,
            debug=False)),
    test_cfg=dict(
        rpn=dict(
            nms_pre=1000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=0.7),
            min_bbox_size=0),
        rcnn=dict(
            score_thr=0.05,
            nms=dict(type='nms', iou_threshold=0.5),
            max_per_img=100,
            mask_thr_binary=0.5)))
dataset_type = 'CocoDataset'
data_root = '../data/car_data_2/'
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='RandomFlip', flip_ratio=0.5),
    dict(
        type='AutoAugment',
        policies=[[{
            'type':
            'Resize',
            'img_scale': [(480, 1333), (512, 1333), (544, 1333), (576, 1333),
                          (608, 1333), (640, 1333), (672, 1333), (704, 1333),
                          (736, 1333), (768, 1333), (800, 1333)],
            'multiscale_mode':
            'value',
            'keep_ratio':
            True
        }],
                  [{
                      'type': 'Resize',
                      'img_scale': [(400, 1333), (500, 1333), (600, 1333)],
                      'multiscale_mode': 'value',
                      'keep_ratio': True
                  }, {
                      'type': 'RandomCrop',
                      'crop_type': 'absolute_range',
                      'crop_size': (384, 600),
                      'allow_negative_crop': True
                  }, {
                      'type':
                      'Resize',
                      'img_scale': [(480, 1333), (512, 1333), (544, 1333),
                                    (576, 1333), (608, 1333), (640, 1333),
                                    (672, 1333), (704, 1333), (736, 1333),
                                    (768, 1333), (800, 1333)],
                      'multiscale_mode':
                      'value',
                      'override':
                      True,
                      'keep_ratio':
                      True
                  }]]),
    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=(1333, 800),
        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=2,
    workers_per_gpu=2,
    train=dict(
        type='CocoDataset',
        ann_file='annotations/train.json',
        img_prefix='images/train',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
            dict(type='RandomFlip', flip_ratio=0.5),
            dict(
                type='AutoAugment',
                policies=[[{
                    'type':
                    'Resize',
                    'img_scale': [(480, 1333), (512, 1333), (544, 1333),
                                  (576, 1333), (608, 1333), (640, 1333),
                                  (672, 1333), (704, 1333), (736, 1333),
                                  (768, 1333), (800, 1333)],
                    'multiscale_mode':
                    'value',
                    'keep_ratio':
                    True
                }],
                          [{
                              'type': 'Resize',
                              'img_scale': [(400, 1333), (500, 1333),
                                            (600, 1333)],
                              'multiscale_mode': 'value',
                              'keep_ratio': True
                          }, {
                              'type': 'RandomCrop',
                              'crop_type': 'absolute_range',
                              'crop_size': (384, 600),
                              'allow_negative_crop': True
                          }, {
                              'type':
                              'Resize',
                              'img_scale': [(480, 1333), (512, 1333),
                                            (544, 1333), (576, 1333),
                                            (608, 1333), (640, 1333),
                                            (672, 1333), (704, 1333),
                                            (736, 1333), (768, 1333),
                                            (800, 1333)],
                              'multiscale_mode':
                              'value',
                              'override':
                              True,
                              'keep_ratio':
                              True
                          }]]),
            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'])
        ],
        data_root='../data/car_data_2/',
        classes=('V04', 'V03', 'V02', 'V01')),
    val=dict(
        type='CocoDataset',
        ann_file='annotations/val.json',
        img_prefix='images/val',
        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',
                        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_root='../data/car_data_2/',
        classes=('V04', 'V03', 'V02', 'V01')),
    test=dict(
        type='CocoDataset',
        ann_file='annotations/test.json',
        img_prefix='images/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',
                        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_root='../data/car_data_2/',
        classes=('V04', 'V03', 'V02', 'V01')))
evaluation = dict(metric=['bbox', 'segm'])
optimizer = dict(
    type='AdamW',
    lr=0.0025,
    betas=(0.9, 0.999),
    weight_decay=0.05,
    paramwise_cfg=dict(
        custom_keys=dict(
            absolute_pos_embed=dict(decay_mult=0.0),
            relative_position_bias_table=dict(decay_mult=0.0),
            norm=dict(decay_mult=0.0))))
optimizer_config = dict(
    grad_clip=None,
    type='DistOptimizerHook',
    update_interval=1,
    coalesce=True,
    bucket_size_mb=-1,
    use_fp16=True)
lr_config = dict(
    policy='step',
    warmup=None,
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[8, 11])
runner = dict(type='EpochBasedRunnerAmp', max_epochs=12)
checkpoint_config = dict(interval=12)
log_config = dict(interval=10, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = '../checkpoints/mask_rcnn_swin_tiny_patch4_window7_1x.pth'
resume_from = None
workflow = [('train', 1)]
fp16 = None
work_dir = './car_exps'
seed = 0
gpu_ids = range(0, 1)

I changed nms.iou_threshold, 0.6 to 0.8, but it cannot fix these issues.

How can I fix these issues on results?

Thanks for reading this.

jshilong commented 3 years ago

Because NMS only is applied to predictions of the same class, if you hope to do it cross-class, you can set class_agnostic to 

    test_cfg=dict(
        rpn=dict(
            nms_pre=1000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=0.7),
            min_bbox_size=0),
        rcnn=dict(
            score_thr=0.05,
            nms=dict(type='nms', iou_threshold=0.5, class_agnostic=True),
            max_per_img=100,
            mask_thr_binary=0.5)))
accforaus commented 3 years ago

Because NMS only is applied to predictions of the same class, if you hope to do it cross-class, you can set class_agnostic to

    test_cfg=dict(
        rpn=dict(
            nms_pre=1000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=0.7),
            min_bbox_size=0),
        rcnn=dict(
            score_thr=0.05,
            nms=dict(type='nms', iou_threshold=0.5, class_agnostic=True),
            max_per_img=100,
            mask_thr_binary=0.5)))

Thanks a lot! It looks clear when I set class_agnostic you advised! you saved my time!