Can I close the instance segmentation and only use object detection?

[Atom-Jinny]

Hi, I am using the model-htc_hrnetv2p_w40_20e_coco.py.But actually I run the other model before,like yolo and my dataset's type is VOC which only has the boxes and donex't have the mask.And the coco needs the 'segmentation' the format :

        {
            "segmentation": [],
            "iscrowd": 0,
            "image_id": 1,
            "area": 2800,
            "bbox": [
                234,
                777,
                56,
                50
            ],
            "category_id": 1,
            "id": 2
        }

btw, I try to use VOC format to run the model and make a new config

_base_ = [
    '../_base_/datasets/voc0712.py',
    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
]
# model settings
model = dict(
    type='HybridTaskCascade',
    pretrained='open-mmlab://msra/hrnetv2_w40',
    backbone=dict(
        #_delete_=True,
        type='HRNet',
        extra=dict(
            stage1=dict(
                num_modules=1,
                num_branches=1,
                block='BOTTLENECK',
                num_blocks=(4, ),
                num_channels=(64, )),
            stage2=dict(
                num_modules=1,
                num_branches=2,
                block='BASIC',
                num_blocks=(4, 4),
                num_channels=(40, 80)),
            stage3=dict(
                num_modules=4,
                num_branches=3,
                block='BASIC',
                num_blocks=(4, 4, 4),
                num_channels=(40, 80, 160)),
            stage4=dict(
                num_modules=3,
                num_branches=4,
                block='BASIC',
                num_blocks=(4, 4, 4, 4),
                num_channels=(40,80,160,320)))),
    neck=dict(
         #_delete_=True,
        type='HRFPN',
        in_channels=[40, 80, 160, 320],
        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],
            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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
    roi_head=dict(
        type='HybridTaskCascadeRoIHead',
        interleaved=True,
        mask_info_flow=True,
        num_stages=3,
        stage_loss_weights=[1, 0.5, 0.25],
        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=2,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.1, 0.1, 0.2, 0.2]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=2,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.05, 0.05, 0.1, 0.1]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=256,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=2,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.033, 0.033, 0.067, 0.067]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0))
        ],
        semantic_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[8]),
        semantic_head=dict(
            type='FusedSemanticHead',
            num_ins=5,
            fusion_level=1,
            num_convs=4,
            in_channels=256,
            conv_out_channels=256,
            num_classes=2,
            ignore_label=255,
            loss_weight=0.2),
        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='HTCMaskHead',
                with_conv_res=False,
                num_convs=4,
                in_channels=256,
                conv_out_channels=256,
                num_classes=2,
                loss_mask=dict(
                    type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
            dict(
                type='HTCMaskHead',
                num_convs=4,
                in_channels=256,
                conv_out_channels=256,
                num_classes=2,
                loss_mask=dict(
                    type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)),
            dict(
                type='HTCMaskHead',
                num_convs=4,
                in_channels=256,
                conv_out_channels=256,
                num_classes=2,
                loss_mask=dict(
                    type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))
        ]))
# model training and testing settings
train_cfg = dict(
    rpn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.7,
            neg_iou_thr=0.3,
            min_pos_iou=0.3,
            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=0,
        pos_weight=-1,
        debug=False),
    rpn_proposal=dict(
        nms_across_levels=False,
        nms_pre=2000,
        nms_post=2000,
        max_num=2000,
        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,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.6,
                neg_iou_thr=0.6,
                min_pos_iou=0.6,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.7,
                min_pos_iou=0.7,
                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_across_levels=False,
        nms_pre=1000,
        nms_post=1000,
        max_num=1000,
        nms_thr=0.7,
        min_bbox_size=0),
    rcnn=dict(
        score_thr=0.001,
        nms=dict(type='nms', iou_threshold=0.5),
        max_per_img=100,
        mask_thr_binary=0.5))

data_root = 'data/VOCdevkit/'
dataset_type = 'VOCDataset'

train_pipeline = [dict(type='Resize', img_scale=(1024, 1024), keep_ratio=True)]
test_pipeline = [dict(img_scale=(1024, 1024))]

img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)

data = dict(
    train=dict(
        dataset=dict(
            ann_file= data_root + 'VOC2007/ImageSets/Main/train.txt',
            img_prefix=data_root + 'VOC2007/'
        )),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'VOC2007/ImageSets/Main/val.txt',
        img_prefix=data_root + 'VOC2007/'))
# learning policy
lr_config = dict(step=[24, 54])
total_epochs = 100

and run it,make some error.

  File "tools/train.py", line 185, in <module>
    main()
  File "tools/train.py", line 181, in main
    meta=meta)
  File "/mmdetection/mmdet/apis/train.py", line 150, in train_detector
    runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 125, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 50, in train
    self.run_iter(data_batch, train_mode=True)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 30, in run_iter
    **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/parallel/data_parallel.py", line 67, in train_step
    return self.module.train_step(*inputs[0], **kwargs[0])
  File "/mmdetection/mmdet/models/detectors/base.py", line 246, in train_step
    losses = self(**data)
  File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 84, in new_func
    return old_func(*args, **kwargs)
  File "/mmdetection/mmdet/models/detectors/base.py", line 180, in forward
    return self.forward_train(img, img_metas, **kwargs)
  File "/mmdetection/mmdet/models/detectors/two_stage.py", line 164, in forward_train
    **kwargs)
  File "/mmdetection/mmdet/models/roi_heads/htc_roi_head.py", line 256, in forward_train
    loss_seg = self.semantic_head.loss(semantic_pred, gt_semantic_seg)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 164, in new_func
    return old_func(*args, **kwargs)
  File "/mmdetection/mmdet/models/roi_heads/mask_heads/fused_semantic_head.py", line 104, in loss
    labels = labels.squeeze(1).long()
AttributeError: 'NoneType' object has no attribute 'squeeze'

hope your answer.Thanks a lot

[v-qjqs]

Hi, I guess you may use Cascase RCNN detectors instead of using HTC?

[ZwwWayne]

The train_pipeline and test_pipeline is not correct. See examples in the configs.