[Feature] Support DanceTrack dataset for MOT #543
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,74 @@ | ||
| # dataset settings | ||
| dataset_type = 'DanceTrackDataset' | ||
| 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_track=True), | ||
| dict( | ||
| type='SeqResize', | ||
| img_scale=(1088, 1088), | ||
| share_params=True, | ||
| ratio_range=(0.8, 1.2), | ||
| keep_ratio=True, | ||
| bbox_clip_border=False), | ||
| dict(type='SeqPhotoMetricDistortion', share_params=True), | ||
| dict( | ||
| type='SeqRandomCrop', | ||
| share_params=False, | ||
| crop_size=(1088, 1088), | ||
| bbox_clip_border=False), | ||
| dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5), | ||
| dict(type='SeqNormalize', **img_norm_cfg), | ||
| dict(type='SeqPad', size_divisor=32), | ||
| dict(type='MatchInstances', skip_nomatch=True), | ||
| dict( | ||
| type='VideoCollect', | ||
| keys=[ | ||
| 'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices', | ||
| 'gt_instance_ids' | ||
| ]), | ||
| dict(type='SeqDefaultFormatBundle', ref_prefix='ref') | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict( | ||
| type='MultiScaleFlipAug', | ||
| img_scale=(1088, 1088), | ||
| flip=False, | ||
| transforms=[ | ||
| dict(type='Resize', keep_ratio=True), | ||
| dict(type='RandomFlip'), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='Pad', size_divisor=32), | ||
| dict(type='ImageToTensor', keys=['img']), | ||
| dict(type='VideoCollect', keys=['img']) | ||
| ]) | ||
| ] | ||
| data_root = 'data/dancetrack/' | ||
| data = dict( | ||
| samples_per_gpu=2, | ||
| workers_per_gpu=2, | ||
| train=dict( | ||
| type=dataset_type, | ||
| visibility_thr=-1, | ||
| ann_file=data_root + 'annotations/train_cocoformat.json', | ||
| img_prefix=data_root + 'train', | ||
| ref_img_sampler=dict( | ||
| num_ref_imgs=1, | ||
| frame_range=10, | ||
| filter_key_img=True, | ||
| method='uniform'), | ||
| pipeline=train_pipeline), | ||
| val=dict( | ||
| type=dataset_type, | ||
| ann_file=data_root + 'annotations/val_cocoformat.json', | ||
| img_prefix=data_root + 'val', | ||
| ref_img_sampler=None, | ||
| pipeline=test_pipeline), | ||
| test=dict( | ||
| type=dataset_type, | ||
| ann_file=data_root + 'annotations/val_cocoformat.json', | ||
| img_prefix=data_root + 'val', | ||
| ref_img_sampler=None, | ||
| pipeline=test_pipeline)) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,127 @@ | ||
| _base_ = ['./qdtrack_faster-rcnn_r50_fpn_4e_crowdhuman_mot17-private-half.py'] | ||
| model = dict( | ||
| type='QDTrack', | ||
| detector=dict( | ||
| backbone=dict( | ||
| norm_cfg=dict(requires_grad=False), | ||
| style='caffe', | ||
| init_cfg=dict( | ||
| type='Pretrained', checkpoint='torchvision://resnet50')), | ||
| rpn_head=dict(bbox_coder=dict(clip_border=False)), | ||
| roi_head=dict( | ||
| bbox_head=dict( | ||
| loss_bbox=dict(type='L1Loss', loss_weight=1.0), | ||
| bbox_coder=dict(clip_border=False), | ||
| num_classes=1)), | ||
| init_cfg=dict( | ||
| type='Pretrained', | ||
| checkpoint= # noqa: E251 | ||
| 'https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco-person/faster_rcnn_r50_fpn_1x_coco-person_20201216_175929-d022e227.pth' # noqa: E501 | ||
| )), | ||
| track_head=dict( | ||
| type='QuasiDenseTrackHead', | ||
| 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='QuasiDenseEmbedHead', | ||
| num_convs=4, | ||
| num_fcs=1, | ||
| embed_channels=256, | ||
| norm_cfg=dict(type='GN', num_groups=32), | ||
| loss_track=dict(type='MultiPosCrossEntropyLoss', loss_weight=0.25), | ||
| loss_track_aux=dict( | ||
| type='L2Loss', | ||
| neg_pos_ub=3, | ||
| pos_margin=0, | ||
| neg_margin=0.1, | ||
| hard_mining=True, | ||
| loss_weight=1.0)), | ||
| loss_bbox=dict(type='L1Loss', loss_weight=1.0), | ||
| train_cfg=dict( | ||
| assigner=dict( | ||
| type='MaxIoUAssigner', | ||
| pos_iou_thr=0.7, | ||
| neg_iou_thr=0.5, | ||
| min_pos_iou=0.5, | ||
| match_low_quality=False, | ||
| ignore_iof_thr=-1), | ||
| sampler=dict( | ||
| type='CombinedSampler', | ||
| num=256, | ||
| pos_fraction=0.5, | ||
| neg_pos_ub=3, | ||
| add_gt_as_proposals=True, | ||
| pos_sampler=dict(type='InstanceBalancedPosSampler'), | ||
| neg_sampler=dict(type='RandomSampler')))), | ||
| tracker=dict( | ||
| type='QuasiDenseEmbedTracker', | ||
| init_score_thr=0.9, | ||
| obj_score_thr=0.5, | ||
| match_score_thr=0.5, | ||
| memo_tracklet_frames=30, | ||
| memo_backdrop_frames=1, | ||
| memo_momentum=0.8, | ||
| nms_conf_thr=0.5, | ||
| nms_backdrop_iou_thr=0.3, | ||
| nms_class_iou_thr=0.7, | ||
| with_cats=True, | ||
| match_metric='bisoftmax')) | ||
| img_norm_cfg = dict( | ||
| mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) | ||
| train_pipeline = [ | ||
| dict(type='LoadMultiImagesFromFile', to_float32=True), | ||
| dict(type='SeqLoadAnnotations', with_bbox=True, with_track=True), | ||
| dict( | ||
| type='SeqResize', | ||
| img_scale=(1088, 1088), | ||
| share_params=True, | ||
| ratio_range=(0.8, 1.2), | ||
| keep_ratio=True, | ||
| bbox_clip_border=False), | ||
| dict(type='SeqPhotoMetricDistortion', share_params=True), | ||
| dict( | ||
| type='SeqRandomCrop', | ||
| share_params=False, | ||
| crop_size=(1088, 1088), | ||
| bbox_clip_border=False), | ||
| dict(type='SeqRandomFlip', share_params=True, flip_ratio=0.5), | ||
| dict(type='SeqNormalize', **img_norm_cfg), | ||
| dict(type='SeqPad', size_divisor=32), | ||
| dict(type='MatchInstances', skip_nomatch=True), | ||
| dict( | ||
| type='VideoCollect', | ||
| keys=[ | ||
| 'img', 'gt_bboxes', 'gt_labels', 'gt_match_indices', | ||
| 'gt_instance_ids' | ||
| ]), | ||
| dict(type='SeqDefaultFormatBundle', ref_prefix='ref') | ||
| ] | ||
| test_pipeline = [ | ||
| dict(type='LoadImageFromFile'), | ||
| dict( | ||
| type='MultiScaleFlipAug', | ||
| img_scale=(1088, 1088), | ||
| flip=False, | ||
| transforms=[ | ||
| dict(type='Resize', keep_ratio=True), | ||
| dict(type='RandomFlip'), | ||
| dict(type='Normalize', **img_norm_cfg), | ||
| dict(type='Pad', size_divisor=32), | ||
| dict(type='ImageToTensor', keys=['img']), | ||
| dict(type='VideoCollect', keys=['img']) | ||
| ]) | ||
| ] | ||
| data = dict( | ||
| train=dict(pipeline=train_pipeline), | ||
| val=dict(pipeline=test_pipeline), | ||
| test=dict(pipeline=test_pipeline)) | ||
| # optimizer && learning policy | ||
| optimizer_config = dict( | ||
| _delete_=True, grad_clip=dict(max_norm=35, norm_type=2)) | ||
| lr_config = dict(policy='step', step=[3]) | ||
| # runtime settings | ||
| total_epochs = 4 | ||
| evaluation = dict(metric=['bbox', 'track'], interval=1) | ||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,29 @@ | ||
| # Copyright (c) OpenMMLab. All rights reserved. | ||
| from mmdet.datasets import DATASETS | ||
|
|
||
| from .mot_challenge_dataset import MOTChallengeDataset | ||
|
|
||
|
|
||
| @DATASETS.register_module() | ||
| class DanceTrackDataset(MOTChallengeDataset): | ||
|
There was a problem hiding this comment. Please remove the duplicated codes since we have already inherited from There was a problem hiding this comment. Removed in the new commit. |
||
| """Dataset for DanceTrack: https://github.com/DanceTrack/DanceTrack. | ||
|
|
||
| Most content is inherited from MOTChallengeDataset. | ||
| """ | ||
|
|
||
| def get_benchmark_and_eval_split(self): | ||
| """Get benchmark and dataset split to evaluate. | ||
|
|
||
| Get benchmark from upeper/lower-case image prefix and the dataset | ||
| split to evaluate. | ||
|
|
||
| Returns: | ||
| tuple(string): The first string denotes the type of dataset. | ||
| The second string denots the split of the dataset to eval. | ||
| """ | ||
| SPLIT_TO_EVAL = ['train', 'val'] | ||
| for split_to_eval in SPLIT_TO_EVAL: | ||
| if split_to_eval in self.img_prefix.upper(): | ||
| break | ||
|
|
||
| return 'DanceTrack', split_to_eval | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
After using base config of ./qdtrack_faster-rcnn_r50_fpn_4e_crowdhuman_mot17-private-half.py, some duplicated keys can be removedd
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I realized that it was a fault to set
./qdtrack_faster-rcnn_r50_fpn_4e_crowdhuman_mot17-private-half.pyas a base because it is based on'../../_base_/datasets/mot_challenge.py'while the dancetrack qdtrack config shoule be based on'../../_base_/datasets/dancetrack.py'. I think the right way should be creating a new config based on:Given the rule that different base config files should have no key conflict, the dancetrack qdtrack config file should inherit no config file using
'../../_base_/datasets/mot_challenge.py'. To be precise, if it inherits'../../_base_/datasets/dancetrack.py'and./qdtrack_faster-rcnn_r50_fpn_4e_mot17-private-half.py'at the same time, it raises error