search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.53k stars 9.46k forks source link

AttributeError: 'NoneType' object has no attribute 'squeeze' #3767

Closed mhyeonsoo closed 4 years ago

mhyeonsoo commented 4 years ago

Bug Description I am trying to implement DetectoRS with own custom dataset, and I am getting an error which is AttributeError: 'NoneType' object has no attribute 'squeeze'

Reproduction

  1. What command or script did you run? 
    python tools/train_gs.py configs/detectors/detectors_htc_r50_1x_gs.py

The config I am using is below.

dataset_type = 'myDataset'
data_root = '/shared/data/mydata/'
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[1.0, 1.0, 1.0], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(type='Resize', img_scale=(760, 510), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[1.0, 1.0, 1.0],
        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=(760, 510),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[1.0, 1.0, 1.0],
                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='myDataset',
        ann_file='/shared/data/mydata/train/train_1cls.json',
        img_prefix='/shared/data/mydata/train/result_image/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
            dict(type='Resize', img_scale=(760, 510), keep_ratio=True),
            dict(type='RandomFlip', flip_ratio=0.5),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[1.0, 1.0, 1.0],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(
                type='Collect',
                keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'])
        ]),
    val=dict(
        type='myDataset',
        ann_file='/shared/data/mydata/test/train_1cls.json',
        img_prefix='/shared/data/mydata/test/result_image/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(760, 510),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[1.0, 1.0, 1.0],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]),
    test=dict(
        type='myDataset',
        ann_file='/shared/data/mydata/test/train_1cls.json',
        img_prefix='/shared/data/mydata/test/result_image/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(760, 510),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=True),
                    dict(type='RandomFlip'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[1.0, 1.0, 1.0],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]))
evaluation = dict(metric=['bbox', 'segm'])
optimizer = dict(type='SGD', lr=0.02, 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)
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)]
model = dict(
    type='HybridTaskCascade',
    pretrained='torchvision://resnet50',
    backbone=dict(
        type='DetectoRS_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',
        conv_cfg=dict(type='ConvAWS'),
        sac=dict(type='SAC', use_deform=True),
        stage_with_sac=(False, True, True, True),
        output_img=True),
    neck=dict(
        type='RFP',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        num_outs=5,
        rfp_steps=2,
        aspp_out_channels=64,
        aspp_dilations=(1, 3, 6, 1),
        rfp_backbone=dict(
            rfp_inplanes=256,
            type='DetectoRS_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,
            conv_cfg=dict(type='ConvAWS'),
            sac=dict(type='SAC', use_deform=True),
            stage_with_sac=(False, True, True, True),
            pretrained='torchvision://resnet50',
            style='pytorch')),
    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='SmoothL1Loss', beta=0.1111111111111111, 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=80,
                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=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=80,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0.0, 0.0, 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=80,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0.0, 0.0, 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))
        ],
        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=80,
                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=80,
                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=80,
                loss_mask=dict(
                    type='CrossEntropyLoss', use_mask=True, 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=183,
            ignore_label=255,
            loss_weight=0.2)))
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=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,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.6,
                neg_iou_thr=0.6,
                min_pos_iou=0.6,
                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),
        dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.7,
                min_pos_iou=0.7,
                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=0.7,
        min_bbox_size=0),
    rcnn=dict(
        score_thr=0.05,
        nms=dict(type='nms', iou_threshold=0.5),
        max_per_img=100))
work_dir = './work_dirs/detectors_htc_r50_1x_gs'
gpu_ids = range(0, 1)
  1. What dataset did you use?

I am using my own dataset which has coco format

Environment

Python: 3.7.7 (default, Mar 23 2020, 22:36:06) [GCC 7.3.0]
CUDA available: True
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 10.1, V10.1.243
GPU 0,1,2,3,4,5,6,7: Tesla V100-SXM2-32GB
GCC: gcc (Ubuntu 7.4.0-1ubuntu1~18.04.1) 7.4.0
PyTorch: 1.5.0
PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 10.1
  - NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
  - CuDNN 7.6.3
  - Magma 2.5.2
  - Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_INTERNAL_THREADPOOL_IMPL -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,

TorchVision: 0.6.0a0+82fd1c8
OpenCV: 4.4.0
MMCV: 1.1.2
MMDetection: 2.4.0+11b1ef8
MMDetection Compiler: GCC 7.3
MMDetection CUDA Compiler: 10.1

Error traceback If applicable, paste the error trackback here.

Traceback (most recent call last):
  File "tools/train_gs.py", line 182, in <module>
    main()
  File "tools/train_gs.py", line 178, in main
    meta=meta)
  File "/shared/hsmoon/mmdetection_official/mmdet/apis/train.py", line 143, 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 122, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 32, in train
    **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 "/shared/hsmoon/mmdetection_official/mmdet/models/detectors/base.py", line 234, in train_step
    losses = self(**data)
  File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
    result = self.forward(*input, **kwargs)
  File "/shared/hsmoon/mmdetection_official/mmdet/core/fp16/decorators.py", line 51, in new_func
    return old_func(*args, **kwargs)
  File "/shared/hsmoon/mmdetection_official/mmdet/models/detectors/base.py", line 168, in forward
    return self.forward_train(img, img_metas, **kwargs)
  File "/shared/hsmoon/mmdetection_official/mmdet/models/detectors/two_stage.py", line 164, in forward_train
    **kwargs)
  File "/shared/hsmoon/mmdetection_official/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 "/shared/hsmoon/mmdetection_official/mmdet/core/fp16/decorators.py", line 131, in new_func
    return old_func(*args, **kwargs)
  File "/shared/hsmoon/mmdetection_official/mmdet/models/roi_heads/mask_heads/fused_semantic_head.py", line 105, in loss
    labels = labels.squeeze(1).long()
AttributeError: 'NoneType' object has no attribute 'squeeze'

When I debugged, I could see that pred_mask in fused_semantic_head.py has values which are not 0, but the labels was None. Could anyone suggest me the solution that I can try with?

Thank you!

v-qjqs commented 4 years ago

Hi, since you include semantic_head, 'with_seg' in LoadAnnotations should be manually set to true.

mhyeonsoo commented 4 years ago

I found that detectoRS with htc does not use semantic segmentation, but I still can meet the error about not existence of semantic segmentation map. Why it requires map although it is without-semantic-seg option?

v-qjqs commented 4 years ago

Hi, since you add 'semantic_roi_extractor' and 'semantic_head' in your config, try to remove these.