search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.21k stars 9.4k forks source link

ValueError: need at least one array to concatenate For htc #4402

Closed Skr20200701 closed 3 years ago

Skr20200701 commented 3 years ago

2021-01-06 16:27:00,066 - mmdet - INFO - Environment info:

sys.platform: linux Python: 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0] CUDA available: True GPU 0: GeForce RTX 2080 Ti CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 10.2, V10.2.89 GCC: gcc (Uos 8.3.0.3-3+rebuild) 8.3.0 PyTorch: 1.6.0 PyTorch compiling details: PyTorch built with:

TorchVision: 0.7.0 OpenCV: 4.4.0 MMCV: 1.2.1 MMCV Compiler: GCC 8.3 MMCV CUDA Compiler: 10.2 MMDetection: 2.7.0+3e902c3

2021-01-06 16:27:00,354 - mmdet - INFO - Distributed training: False 2021-01-06 16:27:00,636 - mmdet - INFO - Config: dataset_type = 'XipanDataset' classes = ('crane', 'car') data_root = '/home/remon/xipan/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, with_seg=True), dict(type='Resize', img_scale=(1920, 1080), 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='SegRescale', scale_factor=0.125), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1920, 1080), flip=False, transforms=[ dict(type='Resize', 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='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ] data = dict( samples_per_gpu=1, workers_per_gpu=1, train=dict( classes=('crane', 'car'), type='XipanDataset', ann_file='/home/remon/xipan/coco/annotations/instances_train2017.json', img_prefix='/home/remon/xipan/coco/train2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=True), dict(type='Resize', img_scale=(1920, 1080), 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='SegRescale', scale_factor=0.125), dict(type='DefaultFormatBundle'), dict( type='Collect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg' ]) ], seg_prefix='/home/remon/xipan/coco/stuffthingmaps/train2017/'), val=dict( classes=('crane', 'car'), type='XipanDataset', ann_file='/home/remon/xipan/coco/annotations/instances_val2017.json', img_prefix='/home/remon/xipan/coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1920, 1080), flip=False, transforms=[ dict(type='Resize', 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='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ]), test=dict( classes=('crane', 'car'), type='XipanDataset', ann_file='/home/remon/xipan/coco/annotations/instances_val2017.json', img_prefix='/home/remon/xipan/coco/val2017/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1920, 1080), flip=False, transforms=[ dict(type='Resize', 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='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']) ]) ])) evaluation = dict(metric=['bbox', 'segm']) optimizer = dict(type='SGD', lr=0.0025, 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=[16, 19]) total_epochs = 20 checkpoint_config = dict(interval=1) log_config = dict( interval=50, hooks=[dict(type='TextLoggerHook'), dict(type='TensorboardLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] model = dict( type='HybridTaskCascade', pretrained='open-mmlab://resnext101_64x4d', backbone=dict( type='ResNeXt', depth=101, 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', groups=16, base_width=4), 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='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=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=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, 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, 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=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)) ], 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))) 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)) work_dir = './work_dirs/htc_x101_64x4d_fpn_16x1_20e_coco' gpu_ids = range(0, 1)

args.seed: None exp_name: htc_x101_64x4d_fpn_16x1_20e_coco.py 2021-01-06 16:27:01,241 - mmdet - INFO - load model from: open-mmlab://resnext101_64x4d 2021-01-06 16:27:01,361 - mmdet - WARNING - The model and loaded state dict do not match exactly

size mismatch for layer1.0.conv1.weight: copying a param with shape torch.Size([256, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 64, 1, 1]). size mismatch for layer1.0.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.conv2.weight: copying a param with shape torch.Size([256, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 4, 3, 3]). size mismatch for layer1.0.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.0.conv3.weight: copying a param with shape torch.Size([256, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer1.1.conv1.weight: copying a param with shape torch.Size([256, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer1.1.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.conv2.weight: copying a param with shape torch.Size([256, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 4, 3, 3]). size mismatch for layer1.1.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.1.conv3.weight: copying a param with shape torch.Size([256, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer1.2.conv1.weight: copying a param with shape torch.Size([256, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([64, 256, 1, 1]). size mismatch for layer1.2.bn1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn1.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn1.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.conv2.weight: copying a param with shape torch.Size([256, 4, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 4, 3, 3]). size mismatch for layer1.2.bn2.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn2.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn2.running_mean: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.bn2.running_var: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for layer1.2.conv3.weight: copying a param with shape torch.Size([256, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 64, 1, 1]). size mismatch for layer2.0.conv1.weight: copying a param with shape torch.Size([512, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 256, 1, 1]). size mismatch for layer2.0.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.conv2.weight: copying a param with shape torch.Size([512, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 8, 3, 3]). size mismatch for layer2.0.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.0.conv3.weight: copying a param with shape torch.Size([512, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer2.1.conv1.weight: copying a param with shape torch.Size([512, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for layer2.1.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.conv2.weight: copying a param with shape torch.Size([512, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 8, 3, 3]). size mismatch for layer2.1.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.1.conv3.weight: copying a param with shape torch.Size([512, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer2.2.conv1.weight: copying a param with shape torch.Size([512, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for layer2.2.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.conv2.weight: copying a param with shape torch.Size([512, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 8, 3, 3]). size mismatch for layer2.2.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.2.conv3.weight: copying a param with shape torch.Size([512, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer2.3.conv1.weight: copying a param with shape torch.Size([512, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 512, 1, 1]). size mismatch for layer2.3.bn1.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn1.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn1.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn1.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.conv2.weight: copying a param with shape torch.Size([512, 8, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 8, 3, 3]). size mismatch for layer2.3.bn2.weight: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn2.bias: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn2.running_mean: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.bn2.running_var: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([128]). size mismatch for layer2.3.conv3.weight: copying a param with shape torch.Size([512, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 128, 1, 1]). size mismatch for layer3.0.conv1.weight: copying a param with shape torch.Size([1024, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 512, 1, 1]). size mismatch for layer3.0.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.0.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.0.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.1.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.1.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.1.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.1.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.2.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.2.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.2.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.2.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.3.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.3.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.3.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.3.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.4.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.4.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.4.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.4.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.5.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.5.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.5.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.5.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.6.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.6.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.6.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.6.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.7.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.7.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.7.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.7.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.8.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.8.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.8.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.8.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.9.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.9.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.9.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.9.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.10.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.10.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.10.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.10.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.11.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.11.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.11.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.11.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.12.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.12.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.12.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.12.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.13.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.13.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.13.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.13.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.14.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.14.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.14.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.14.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.15.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.15.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.15.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.15.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.16.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.16.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.16.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.16.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.17.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.17.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.17.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.17.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.18.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.18.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.18.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.18.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.19.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.19.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.19.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.19.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.20.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.20.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.20.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.20.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.21.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.21.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.21.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.21.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer3.22.conv1.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([256, 1024, 1, 1]). size mismatch for layer3.22.bn1.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.bn1.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.bn1.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.bn1.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.conv2.weight: copying a param with shape torch.Size([1024, 16, 3, 3]) from checkpoint, the shape in current model is torch.Size([256, 16, 3, 3]). size mismatch for layer3.22.bn2.weight: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.bn2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.bn2.running_mean: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.bn2.running_var: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([256]). size mismatch for layer3.22.conv3.weight: copying a param with shape torch.Size([1024, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([1024, 256, 1, 1]). size mismatch for layer4.0.conv1.weight: copying a param with shape torch.Size([2048, 1024, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 1024, 1, 1]). size mismatch for layer4.0.bn1.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn1.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn1.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn1.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.conv2.weight: copying a param with shape torch.Size([2048, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 32, 3, 3]). size mismatch for layer4.0.bn2.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn2.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn2.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.bn2.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.0.conv3.weight: copying a param with shape torch.Size([2048, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 512, 1, 1]). size mismatch for layer4.1.conv1.weight: copying a param with shape torch.Size([2048, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 2048, 1, 1]). size mismatch for layer4.1.bn1.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn1.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn1.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn1.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.conv2.weight: copying a param with shape torch.Size([2048, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 32, 3, 3]). size mismatch for layer4.1.bn2.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn2.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn2.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.bn2.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.1.conv3.weight: copying a param with shape torch.Size([2048, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 512, 1, 1]). size mismatch for layer4.2.conv1.weight: copying a param with shape torch.Size([2048, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([512, 2048, 1, 1]). size mismatch for layer4.2.bn1.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn1.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn1.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn1.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.conv2.weight: copying a param with shape torch.Size([2048, 32, 3, 3]) from checkpoint, the shape in current model is torch.Size([512, 32, 3, 3]). size mismatch for layer4.2.bn2.weight: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn2.bias: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn2.running_mean: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.bn2.running_var: copying a param with shape torch.Size([2048]) from checkpoint, the shape in current model is torch.Size([512]). size mismatch for layer4.2.conv3.weight: copying a param with shape torch.Size([2048, 2048, 1, 1]) from checkpoint, the shape in current model is torch.Size([2048, 512, 1, 1]). loading annotations into memory... Done (t=0.01s) creating index... index created! loading annotations into memory... Done (t=0.00s) creating index... index created! [<torch.utils.data.dataloader.DataLoader object at 0x7fe69d809c90>] [('train', 1)] 20 2021-01-06 16:27:02,934 - mmdet - INFO - Start running, host: remon@remon-PC, work_dir: /home/remon/mmdetection2.7/work_dirs/htc_x101_64x4d_fpn_16x1_20e_coco 2021-01-06 16:27:02,934 - mmdet - INFO - workflow: [('train', 1)], max: 20 epochs Traceback (most recent call last): File "./tools/train.py", line 182, in main() File "./tools/train.py", line 178, in main meta=meta) File "/home/remon/mmdetection2.7/mmdet/apis/train.py", line 150, in train_detector runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/remon/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 125, in run epoch_runner(data_loaders[i], **kwargs) File "/home/remon/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 47, in train for i, data_batch in enumerate(self.data_loader): File "/home/remon/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 291, in iter return _MultiProcessingDataLoaderIter(self) File "/home/remon/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 764, in init self._try_put_index() File "/home/remon/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 994, in _try_put_index index = self._next_index() File "/home/remon/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 357, in _next_index return next(self._sampler_iter) # may raise StopIteration File "/home/remon/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/data/sampler.py", line 208, in iter for idx in self.sampler: File "/home/remon/mmdetection2.7/mmdet/datasets/samplers/group_sampler.py", line 36, in iter indices = np.concatenate(indices) File "<__array_function__ internals>", line 6, in concatenate ValueError: need at least one array to concatenate

Bug fix If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

v-qjqs commented 3 years ago

Hi, the above error is caused by concatenating from an empty indices. And the empty indices should be caused by the empty dataset.flag. But I'm not sure whether this is caused by an empty data_infos or not.

Here (Reorganize new data formats to existing format) we give a more detailed docs for training your customized dataset with COCO format under MMDetection.