search

SwinTransformer / Swin-Transformer-Object-Detection

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.
https://arxiv.org/abs/2103.14030
Apache License 2.0
1.81k stars 381 forks source link

Mask RCNN pretrained error #33

Closed WuNein closed 3 years ago

WuNein commented 3 years ago

I have already tried tiny and small version, none of them can run. When train without pretrained weight, it is works fine, but time is a problem. The following is the configs :

model = dict(
    type='MaskRCNN',
    pretrained='mask_rcnn_swin_tiny_patch4_window7.pth',
    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=0.2,
        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=43,
            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=43,
            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/coco/'
customed = [
    'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
    'speedlimit-70', 'speedlimit-80', 'restrict-end-80', 'speedlimit-100',
    'speedlimit-120', 'no-overtake', 'no-overtake-truck',
    'priority-next-intersect', 'priority-road', 'giveaway', 'stop',
    'no-traffic-bothways', 'no-truck', 'no-entry', 'danger', 'bend-left',
    'bend-right', 'bend', 'uneven-road', 'slippery-road', 'road-narrow',
    'construction', 'traffic-signal', 'pedestrian-crossing', 'school-crossing',
    'cycle-crossing', 'snow', 'animals', 'restriction-ends', 'go-right',
    'go-left', 'go-straight', 'go-right-straight', 'go-left-straight',
    'keep-right', 'keep-left', 'roundabout', 'restrict-ends-overtaking',
    'restrict-ends-overtaking-truck'
]
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='data/coco/annotations/instances_train2017.json',
        img_prefix='data/coco/train2017/',
        classes=[
            'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
            'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
            'speedlimit-100', 'speedlimit-120', 'no-overtake',
            'no-overtake-truck', 'priority-next-intersect', 'priority-road',
            'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
            'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
            'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
            'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
            'animals', 'restriction-ends', 'go-right', 'go-left',
            'go-straight', 'go-right-straight', 'go-left-straight',
            'keep-right', 'keep-left', 'roundabout',
            'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
        ],
        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'])
        ]),
    val=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        img_prefix='data/coco/val2017/',
        classes=[
            'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
            'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
            'speedlimit-100', 'speedlimit-120', 'no-overtake',
            'no-overtake-truck', 'priority-next-intersect', 'priority-road',
            'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
            'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
            'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
            'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
            'animals', 'restriction-ends', 'go-right', 'go-left',
            'go-straight', 'go-right-straight', 'go-left-straight',
            'keep-right', 'keep-left', 'roundabout',
            'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
        ],
        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'])
                ])
        ]),
    test=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        img_prefix='data/coco/val2017/',
        classes=[
            'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
            'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
            'speedlimit-100', 'speedlimit-120', 'no-overtake',
            'no-overtake-truck', 'priority-next-intersect', 'priority-road',
            'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
            'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
            'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
            'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
            'animals', 'restriction-ends', 'go-right', 'go-left',
            'go-straight', 'go-right-straight', 'go-left-straight',
            'keep-right', 'keep-left', 'roundabout',
            'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
        ],
        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'])
                ])
        ]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(
    type='AdamW',
    lr=0.0001,
    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='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[27, 33])
runner = dict(type='EpochBasedRunnerAmp', max_epochs=36)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
fp16 = None
work_dir = './work_dirs/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_3x_coco'
gpu_ids = range(0, 1)
KeyError: "Mask RCNN: 'backbone.layers.0.blocks.0.attn.relative position bias table'"
WuNein commented 3 years ago

Update 1.0.3 Still, with no pretrained weight is fine

2021-05-12 01:59:13,749 - mmdet - INFO - Epoch [1][50/244]  lr: 9.890e-06, eta: 0:30:01, time: 0.626, data_time: 0.057, memory: 2233, loss_rpn_cls: 0.6614, loss_rpn_bbox: 0.0178, loss_cls: 2.6993, acc: 71.3789, loss_bbox: 0.0027, loss_mask: 1.2777, loss: 4.6589

With pretrained , same error

/content/Swin-Transformer-Object-Detection
2021-05-12 02:03:35,907 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.7.10 (default, May  3 2021, 02:48:31) [GCC 7.5.0]
CUDA available: True
GPU 0: Tesla T4
CUDA_HOME: /usr/local/cuda
NVCC: Build cuda_11.0_bu.TC445_37.28845127_0
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.8.1+cu101
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 v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  - 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_70,code=sm_70
  - CuDNN 7.6.3
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=10.1, CUDNN_VERSION=7.6.3, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -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-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -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, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.8.1, USE_CUDA=ON, USE_CUDNN=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, 

TorchVision: 0.9.1+cu101
OpenCV: 4.1.2
MMCV: 1.3.2
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 10.1
MMDetection: 2.11.0+41bb93f
------------------------------------------------------------

2021-05-12 02:03:39,227 - mmdet - INFO - Distributed training: False
2021-05-12 02:03:42,486 - mmdet - INFO - Config:
model = dict(
    type='MaskRCNN',
    pretrained=
    '/content/Swin-Transformer-Object-Detection/mask_rcnn_swin_tiny_patch4_window7_1x.pth',
    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=True),
    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=43,
            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=43,
            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/coco/'
customed = [
    'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
    'speedlimit-70', 'speedlimit-80', 'restrict-end-80', 'speedlimit-100',
    'speedlimit-120', 'no-overtake', 'no-overtake-truck',
    'priority-next-intersect', 'priority-road', 'giveaway', 'stop',
    'no-traffic-bothways', 'no-truck', 'no-entry', 'danger', 'bend-left',
    'bend-right', 'bend', 'uneven-road', 'slippery-road', 'road-narrow',
    'construction', 'traffic-signal', 'pedestrian-crossing', 'school-crossing',
    'cycle-crossing', 'snow', 'animals', 'restriction-ends', 'go-right',
    'go-left', 'go-straight', 'go-right-straight', 'go-left-straight',
    'keep-right', 'keep-left', 'roundabout', 'restrict-ends-overtaking',
    'restrict-ends-overtaking-truck'
]
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='data/coco/annotations/instances_train2017.json',
        img_prefix='data/coco/train2017/',
        classes=[
            'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
            'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
            'speedlimit-100', 'speedlimit-120', 'no-overtake',
            'no-overtake-truck', 'priority-next-intersect', 'priority-road',
            'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
            'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
            'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
            'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
            'animals', 'restriction-ends', 'go-right', 'go-left',
            'go-straight', 'go-right-straight', 'go-left-straight',
            'keep-right', 'keep-left', 'roundabout',
            'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
        ],
        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'])
        ]),
    val=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        classes=[
            'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
            'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
            'speedlimit-100', 'speedlimit-120', 'no-overtake',
            'no-overtake-truck', 'priority-next-intersect', 'priority-road',
            'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
            'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
            'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
            'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
            'animals', 'restriction-ends', 'go-right', 'go-left',
            'go-straight', 'go-right-straight', 'go-left-straight',
            'keep-right', 'keep-left', 'roundabout',
            'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
        ],
        img_prefix='data/coco/val2017/',
        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'])
                ])
        ]),
    test=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        classes=[
            'speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
            'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
            'speedlimit-100', 'speedlimit-120', 'no-overtake',
            'no-overtake-truck', 'priority-next-intersect', 'priority-road',
            'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
            'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
            'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
            'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
            'animals', 'restriction-ends', 'go-right', 'go-left',
            'go-straight', 'go-right-straight', 'go-left-straight',
            'keep-right', 'keep-left', 'roundabout',
            'restrict-ends-overtaking', 'restrict-ends-overtaking-truck'
        ],
        img_prefix='data/coco/val2017/',
        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'])
                ])
        ]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(
    type='AdamW',
    lr=0.0001,
    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='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[8, 11])
runner = dict(type='EpochBasedRunnerAmp', max_epochs=12)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
fp16 = None
work_dir = './work_dirs/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco'
gpu_ids = range(0, 1)

2021-05-12 02:03:42,927 - mmdet - INFO - load model from: /content/Swin-Transformer-Object-Detection/mask_rcnn_swin_tiny_patch4_window7_1x.pth
Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 51, in build_from_cfg
    return obj_cls(**args)
  File "/content/Swin-Transformer-Object-Detection/mmdet/models/detectors/mask_rcnn.py", line 24, in __init__
    pretrained=pretrained)
  File "/content/Swin-Transformer-Object-Detection/mmdet/models/detectors/two_stage.py", line 48, in __init__
    self.init_weights(pretrained=pretrained)
  File "/content/Swin-Transformer-Object-Detection/mmdet/models/detectors/two_stage.py", line 68, in init_weights
    self.backbone.init_weights(pretrained=pretrained)
  File "/content/Swin-Transformer-Object-Detection/mmdet/models/backbones/swin_transformer.py", line 594, in init_weights
    load_checkpoint(self, pretrained, strict=False, logger=logger)
  File "/content/Swin-Transformer-Object-Detection/mmcv_custom/checkpoint.py", line 340, in load_checkpoint
    table_current = model.state_dict()[table_key]
KeyError: 'backbone.layers.0.blocks.0.attn.relative_position_bias_table'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/train.py", line 187, in <module>
    main()
  File "tools/train.py", line 161, in main
    test_cfg=cfg.get('test_cfg'))
  File "/content/Swin-Transformer-Object-Detection/mmdet/models/builder.py", line 77, in build_detector
    return build(cfg, DETECTORS, dict(train_cfg=train_cfg, test_cfg=test_cfg))
  File "/content/Swin-Transformer-Object-Detection/mmdet/models/builder.py", line 34, in build
    return build_from_cfg(cfg, registry, default_args)
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 54, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
KeyError: "MaskRCNN: 'backbone.layers.0.blocks.0.attn.relative_position_bias_table'"
kentaroy47 commented 3 years ago

You should not call pretrained inside the model dict.

see: https://mmdetection.readthedocs.io/en/latest/tutorials/finetune.html

Use pre-trained model
To use the pre-trained model, the new config add the link of pre-trained models in the load_from. The users might need to download the model weights before training to avoid the download time during training.

load_from = 'http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth'  # noqa

Just adding load_from at the end of your config should work fine.

WuNein commented 3 years ago

You should not call pretrained inside the model dict.

see: https://mmdetection.readthedocs.io/en/latest/tutorials/finetune.html

Use pre-trained model
To use the pre-trained model, the new config add the link of pre-trained models in the load_from. The users might need to download the model weights before training to avoid the download time during training.

load_from = 'http://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco/mask_rcnn_r50_caffe_fpn_mstrain-poly_3x_coco_bbox_mAP-0.408__segm_mAP-0.37_20200504_163245-42aa3d00.pth'  # noqa

Just adding load_from at the end of your config should work fine.

Problem solved BTW, Mask RNN can only use coco with segmentation Cannot set to withmask = false

/content/Swin-Transformer-Object-Detection
2021-05-12 06:49:33,536 - mmdet - INFO - Environment info:
------------------------------------------------------------
sys.platform: linux
Python: 3.7.10 (default, May  3 2021, 02:48:31) [GCC 7.5.0]
CUDA available: True
GPU 0: Tesla K80
CUDA_HOME: /usr/local/cuda
NVCC: Build cuda_11.0_bu.TC445_37.28845127_0
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.8.1+cu101
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 v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  - 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_70,code=sm_70
  - CuDNN 7.6.3
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=10.1, CUDNN_VERSION=7.6.3, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -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-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -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, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.8.1, USE_CUDA=ON, USE_CUDNN=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, 

TorchVision: 0.9.1+cu101
OpenCV: 4.1.2
MMCV: 1.3.2
MMCV Compiler: GCC 7.3
MMCV CUDA Compiler: 10.1
MMDetection: 2.11.0+41bb93f
------------------------------------------------------------

2021-05-12 06:49:37,757 - mmdet - INFO - Distributed training: False
2021-05-12 06:49:41,963 - mmdet - INFO - Config:
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=True),
    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=43,
            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=43,
            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/coco/'
customed = ('speedlimit-20', 'speedlimit-30', 'speedlimit-50', 'speedlimit-60',
            'speedlimit-70', 'speedlimit-80', 'restrict-end-80',
            'speedlimit-100', 'speedlimit-120', 'no-overtake',
            'no-overtake-truck', 'priority-next-intersect', 'priority-road',
            'giveaway', 'stop', 'no-traffic-bothways', 'no-truck', 'no-entry',
            'danger', 'bend-left', 'bend-right', 'bend', 'uneven-road',
            'slippery-road', 'road-narrow', 'construction', 'traffic-signal',
            'pedestrian-crossing', 'school-crossing', 'cycle-crossing', 'snow',
            'animals', 'restriction-ends', 'go-right', 'go-left',
            'go-straight', 'go-right-straight', 'go-left-straight',
            'keep-right', 'keep-left', 'roundabout',
            'restrict-ends-overtaking', 'restrict-ends-overtaking-truck')
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='data/coco/annotations/instances_train2017.json',
        img_prefix='data/coco/train2017/',
        classes=('speedlimit-20', 'speedlimit-30', 'speedlimit-50',
                 'speedlimit-60', 'speedlimit-70', 'speedlimit-80',
                 'restrict-end-80', 'speedlimit-100', 'speedlimit-120',
                 'no-overtake', 'no-overtake-truck', 'priority-next-intersect',
                 'priority-road', 'giveaway', 'stop', 'no-traffic-bothways',
                 'no-truck', 'no-entry', 'danger', 'bend-left', 'bend-right',
                 'bend', 'uneven-road', 'slippery-road', 'road-narrow',
                 'construction', 'traffic-signal', 'pedestrian-crossing',
                 'school-crossing', 'cycle-crossing', 'snow', 'animals',
                 'restriction-ends', 'go-right', 'go-left', 'go-straight',
                 'go-right-straight', 'go-left-straight', 'keep-right',
                 'keep-left', 'roundabout', 'restrict-ends-overtaking',
                 'restrict-ends-overtaking-truck'),
        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'])
        ]),
    val=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        classes=('speedlimit-20', 'speedlimit-30', 'speedlimit-50',
                 'speedlimit-60', 'speedlimit-70', 'speedlimit-80',
                 'restrict-end-80', 'speedlimit-100', 'speedlimit-120',
                 'no-overtake', 'no-overtake-truck', 'priority-next-intersect',
                 'priority-road', 'giveaway', 'stop', 'no-traffic-bothways',
                 'no-truck', 'no-entry', 'danger', 'bend-left', 'bend-right',
                 'bend', 'uneven-road', 'slippery-road', 'road-narrow',
                 'construction', 'traffic-signal', 'pedestrian-crossing',
                 'school-crossing', 'cycle-crossing', 'snow', 'animals',
                 'restriction-ends', 'go-right', 'go-left', 'go-straight',
                 'go-right-straight', 'go-left-straight', 'keep-right',
                 'keep-left', 'roundabout', 'restrict-ends-overtaking',
                 'restrict-ends-overtaking-truck'),
        img_prefix='data/coco/val2017/',
        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'])
                ])
        ]),
    test=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        classes=('speedlimit-20', 'speedlimit-30', 'speedlimit-50',
                 'speedlimit-60', 'speedlimit-70', 'speedlimit-80',
                 'restrict-end-80', 'speedlimit-100', 'speedlimit-120',
                 'no-overtake', 'no-overtake-truck', 'priority-next-intersect',
                 'priority-road', 'giveaway', 'stop', 'no-traffic-bothways',
                 'no-truck', 'no-entry', 'danger', 'bend-left', 'bend-right',
                 'bend', 'uneven-road', 'slippery-road', 'road-narrow',
                 'construction', 'traffic-signal', 'pedestrian-crossing',
                 'school-crossing', 'cycle-crossing', 'snow', 'animals',
                 'restriction-ends', 'go-right', 'go-left', 'go-straight',
                 'go-right-straight', 'go-left-straight', 'keep-right',
                 'keep-left', 'roundabout', 'restrict-ends-overtaking',
                 'restrict-ends-overtaking-truck'),
        img_prefix='data/coco/val2017/',
        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'])
                ])
        ]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(
    type='AdamW',
    lr=0.0001,
    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='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[8, 11])
runner = dict(type='EpochBasedRunnerAmp', max_epochs=12)
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = '/content/Swin-Transformer-Object-Detection/mask_rcnn_swin_tiny_patch4_window7_1x.pth'
resume_from = None
workflow = [('train', 1)]
fp16 = None
work_dir = './work_dirs/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco'
gpu_ids = range(0, 1)

loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
Selected optimization level O1:  Insert automatic casts around Pytorch functions and Tensor methods.

Defaults for this optimization level are:
enabled                : True
opt_level              : O1
cast_model_type        : None
patch_torch_functions  : True
keep_batchnorm_fp32    : None
master_weights         : None
loss_scale             : dynamic
Processing user overrides (additional kwargs that are not None)...
After processing overrides, optimization options are:
enabled                : True
opt_level              : O1
cast_model_type        : None
patch_torch_functions  : True
keep_batchnorm_fp32    : None
master_weights         : None
loss_scale             : dynamic
Warning:  multi_tensor_applier fused unscale kernel is unavailable, possibly because apex was installed without --cuda_ext --cpp_ext. Using Python fallback.  Original ImportError was: ModuleNotFoundError("No module named 'amp_C'")
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!
2021-05-12 06:49:45,238 - mmdet - INFO - load checkpoint from /content/Swin-Transformer-Object-Detection/mask_rcnn_swin_tiny_patch4_window7_1x.pth
2021-05-12 06:49:45,238 - mmdet - INFO - Use load_from_local loader
2021-05-12 06:49:45,396 - mmdet - WARNING - The model and loaded state dict do not match exactly

size mismatch for roi_head.bbox_head.fc_cls.weight: copying a param with shape torch.Size([81, 1024]) from checkpoint, the shape in current model is torch.Size([44, 1024]).
size mismatch for roi_head.bbox_head.fc_cls.bias: copying a param with shape torch.Size([81]) from checkpoint, the shape in current model is torch.Size([44]).
size mismatch for roi_head.bbox_head.fc_reg.weight: copying a param with shape torch.Size([320, 1024]) from checkpoint, the shape in current model is torch.Size([172, 1024]).
size mismatch for roi_head.bbox_head.fc_reg.bias: copying a param with shape torch.Size([320]) from checkpoint, the shape in current model is torch.Size([172]).
size mismatch for roi_head.mask_head.conv_logits.weight: copying a param with shape torch.Size([80, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([43, 256, 1, 1]).
size mismatch for roi_head.mask_head.conv_logits.bias: copying a param with shape torch.Size([80]) from checkpoint, the shape in current model is torch.Size([43]).
2021-05-12 06:49:45,400 - mmdet - INFO - Start running, host: root@00aec1052d18, work_dir: /content/Swin-Transformer-Object-Detection/work_dirs/mask_rcnn_swin_tiny_patch4_window7_mstrain_480-800_adamw_1x_coco
2021-05-12 06:49:45,400 - mmdet - INFO - workflow: [('train', 1)], max: 12 epochs
Gradient overflow.  Skipping step, loss scaler 0 reducing loss scale to 32768.0
Gradient overflow.  Skipping step, loss scaler 0 reducing loss scale to 16384.0
Gradient overflow.  Skipping step, loss scaler 0 reducing loss scale to 8192.0
Gradient overflow.  Skipping step, loss scaler 0 reducing loss scale to 4096.0
Gradient overflow.  Skipping step, loss scaler 0 reducing loss scale to 2048.0
sjtuytc commented 2 years ago

e_

We can actually set with_mask=False.