TypeError: CocoDataset: string indices must be integers

[jiangxinufo]

unexpected key in source state_dict: fc.weight, fc.bias

E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\mmdet\datasets\custom.py:154: UserWarning: CustomDataset does not support filtering empty gt images. warnings.warn( Traceback (most recent call last): File "e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmcv-1.3.1\mmcv\utils\registry.py", line 51, in build_from_cfg return obj_cls(**args) File "E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\mmdet\datasets\custom.py", line 96, in init valid_inds = self._filter_imgs() File "E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\mmdet\datasets\custom.py", line 158, in _filter_imgs if min(img_info['width'], img_info['height']) >= min_size: TypeError: string indices must be integers

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "E:/mmdetection/week2_mmdet/Week2_mmdet/mmdetection-2.11.0/tools/train.py", line 187, in main() File "E:/mmdetection/week2_mmdet/Week2_mmdet/mmdetection-2.11.0/tools/train.py", line 163, in main datasets = [build_dataset(cfg.data.train)] File "E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\mmdet\datasets\builder.py", line 71, in build_dataset dataset = build_from_cfg(cfg, DATASETS, default_args) File "e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmcv-1.3.1\mmcv\utils\registry.py", line 54, in build_from_cfg raise type(e)(f'{obj_cls.name}: {e}') TypeError: CocoDataset: string indices must be integers

[jiangxinufo]

def _filter_imgs(self, min_size=32): """Filter images too small.""" if self.filter_empty_gt: warnings.warn( 'CustomDataset does not support filtering empty gt images.') valid_inds = [] for i, img_info in enumerate(self.data_infos): if min(img_info['width'], img_info['height']) >= min_size: //img_info有错误 valid_inds.append(i) return valid_inds

[jiangxinufo]

2021-11-10 13:33:03,259 - mmdet - INFO - Distributed training: False 2021-11-10 13:33:04,464 - mmdet - INFO - Config: model = dict( type='MaskRCNN', pretrained='torchvision://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, norm_cfg=dict(type='BN', requires_grad=True), norm_eval=True, style='pytorch'), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[8], ratios=[0.5, 1.0, 2.0], strides=[4, 8, 16, 32, 64]), bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0]), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), roi_head=dict( type='StandardRoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='Shared2FCBBoxHead', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=2, 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=2, 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=0.4), min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_threshold=0.4), max_per_img=100, mask_thr_binary=0.5))) dataset_type = 'CocoDataset' data_root = 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\tools\data\coco/' 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='Resize', img_scale=(500, 300), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), 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=(500, 300), 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=4, train=dict( type='CocoDataset', ann_file= 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\tools\data\coco/annotations/instances_train2017.json', img_prefix= 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\tools\data\coco/train2017/', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='Resize', img_scale=(500, 300), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), 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= 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\tools\data\coco/annotations/instances_val2017.json', img_prefix= 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\tools\data\coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(500, 300), 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= 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\tools\data\coco/annotations/instances_val2017.json', img_prefix= 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\tools\data\coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(500, 300), 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(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=[20, 25]) runner = dict(type='EpochBasedRunner', max_epochs=30) checkpoint_config = dict(interval=4) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) custom_hooks = [dict(type='NumClassCheckHook')] dist_params = dict(backend='nccl') log_level = 'INFO' load_from = 'E:\mmdetection\week2_mmdet\Week2_mmdet\mmdetection-2.11.0\weights\mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth' resume_from = None workflow = [('train', 1)] work_dir = 'train_grain_128' gpu_ids = range(0, 1)

2021-11-10 13:33:04,862 - mmdet - INFO - load model from: torchvision://resnet50 2021-11-10 13:33:04,863 - mmdet - INFO - Use load_from_torchvision loader 2021-11-10 13:33:05,231 - mmdet - WARNING - The model and loaded state dict do not match exactly

unexpected key in source state_dict: fc.weight, fc.bias

e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmdet\datasets\custom.py:155: UserWarning: CustomDataset does not support filtering empty gt images. 'CustomDataset does not support filtering empty gt images.') Traceback (most recent call last): File "e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmcv-1.3.1\mmcv\utils\registry.py", line 51, in build_from_cfg return obj_cls(**args) File "e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmdet\datasets\custom.py", line 96, in init valid_inds = self._filter_imgs() File "e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmdet\datasets\custom.py", line 158, in _filter_imgs if min(img_info['width'], img_info['height']) >= min_size: TypeError: string indices must be integers

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "tools/train.py", line 187, in main() File "tools/train.py", line 163, in main datasets = [build_dataset(cfg.data.train)] File "e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmdet\datasets\builder.py", line 71, in build_dataset dataset = build_from_cfg(cfg, DATASETS, default_args) File "e:\mmdetection\week2_mmdet\week2_mmdet\mmdetection-2.11.0\mmcv-1.3.1\mmcv\utils\registry.py", line 54, in build_from_cfg raise type(e)(f'{obj_cls.name}: {e}') TypeError: CocoDataset: string indices must be integers

[hhaAndroid]

@jiangxinufo Please check if your label is correct.

[alaa-shubbak]

I have the same error , and i checked my dataset annotation here is a part of them:

I don't know where is the error /mistake in them. can you please help.