Errors occurred during testing

[fxooooooooo]

1、An error occurred when I ran the following test command

python tools/test.py work_dirs/3.8/masktrack_rcnn_r50_fpn_12e_youtubevis2021.py --checkpoint work_dirs/3.8/latest.pth --out work_dirs/3.9/3.9_test.pkl --eval track_segm

Error:

load checkpoint from local path: work_dirs/3.8/latest.pth [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 13195/13195, 27.3 task/s, elapsed: 483s, ETA: 0s writing results to work_dirs/3.9/3.9_test.pkl Traceback (most recent call last): File "tools/test.py", line 225, in main() File "tools/test.py", line 215, in main metric = dataset.evaluate(outputs, **eval_kwargs) File "/home/lin/Desktop/mmtracking-master/mmtracking/mmtrack/datasets/coco_video_dataset.py", line 402, in evaluate raise KeyError(f'metric {metric} is not supported.') KeyError: 'metric track_segm is not supported.'

My config:

model = dict( detector=dict( type='MaskRCNN', 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', init_cfg=dict( type='Pretrained', checkpoint='torchvision://resnet50')), 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=40, 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=40, 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=64, 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=200, max_per_img=200, 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=128, 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=200, max_per_img=200, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=0), rcnn=dict( score_thr=0.01, nms=dict(type='nms', iou_threshold=0.5), max_per_img=100, mask_thr_binary=0.5)), init_cfg=dict( type='Pretrained', checkpoint= 'https://download.openmmlab.com/mmdetection/v2.0/mask_rcnn/mask_rcnn_r50_fpn_1x_coco/mask_rcnn_r50_fpn_1x_coco_20200205-d4b0c5d6.pth' )), type='MaskTrackRCNN', track_head=dict( type='RoITrackHead', 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]), embed_head=dict( type='RoIEmbedHead', num_fcs=2, roi_feat_size=7, in_channels=256, fc_out_channels=1024), train_cfg=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=128, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), pos_weight=-1, debug=False)), tracker=dict( type='MaskTrackRCNNTracker', match_weights=dict(det_score=1.0, iou=2.0, det_label=10.0), num_frames_retain=20)) 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='LoadMultiImagesFromFile', to_float32=True), dict( type='SeqLoadAnnotations', with_bbox=True, with_mask=True, with_track=True), dict( type='SeqResize', share_params=True, img_scale=(640, 360), keep_ratio=True), dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5), dict( type='SeqNormalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='SeqPad', size_divisor=32), dict( type='VideoCollect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_instance_ids']), dict(type='SeqDefaultFormatBundle', ref_prefix='ref') ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(640, 360), 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='VideoCollect', keys=['img']) ]) ] dataset_type = 'YouTubeVISDataset' data_root = 'data/youtube_vis_2021/' dataset_version = '2021' data = dict( samples_per_gpu=6, workers_per_gpu=2, train=dict( type='YouTubeVISDataset', dataset_version='2021', ann_file= 'data/youtube_vis_2021/annotations/youtube_vis_2021_train.json', img_prefix='data/youtube_vis_2021/train/JPEGImages', ref_img_sampler=dict( num_ref_imgs=1, frame_range=100, filter_key_img=True, method='uniform'), pipeline=[ dict(type='LoadMultiImagesFromFile', to_float32=True), dict( type='SeqLoadAnnotations', with_bbox=True, with_mask=True, with_track=True), dict( type='SeqResize', share_params=True, img_scale=(640, 360), keep_ratio=True), dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5), dict( type='SeqNormalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True), dict(type='SeqPad', size_divisor=32), dict( type='VideoCollect', keys=[ 'img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_instance_ids' ]), dict(type='SeqDefaultFormatBundle', ref_prefix='ref') ]), val=dict( type='YouTubeVISDataset', dataset_version='2021', ann_file= 'data/youtube_vis_2021/annotations/youtube_vis_2021_valid.json', img_prefix='data/youtube_vis_2021/valid/JPEGImages', ref_img_sampler=None, pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(640, 360), 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='VideoCollect', keys=['img']) ]) ]), test=dict( type='YouTubeVISDataset', dataset_version='2021', ann_file= 'data/youtube_vis_2021/annotations/youtube_vis_2021_valid.json', img_prefix='data/youtube_vis_2021/valid/JPEGImages', ref_img_sampler=None, pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(640, 360), 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='VideoCollect', keys=['img']) ]) ])) optimizer = dict(type='SGD', lr=0.00125, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) checkpoint_config = dict(interval=1) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = 'work_dirs/3.8/epoch_7.pth' workflow = [('train', 1)] opencv_num_threads = 0 mp_start_method = 'fork' lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.3333333333333333, step=[8, 11]) total_epochs = 12 evaluation = dict(metric=['track_segm'], interval=13) work_dir = 'work_dirs/3.8' gpu_ids = [0]

[JingweiZhang12]

The evaluation of YoutubeVIS dataset must submit your results to the remote official server rather than evaluate the results locally. Details can be seen https://github.com/open-mmlab/mmtracking/blob/master/docs/en/quick_run.md.