_base_ = ['../_base_/default_runtime.py'] model = dict( type='CrowdDet', data_preprocessor=dict( type='DetDataPreprocessor', mean=[103.53, 116.28, 123.675], std=[57.375, 57.12, 58.395], bgr_to_rgb=False, pad_size_divisor=64, # This option is set according to https://github.com/Purkialo/CrowdDet/ # blob/master/lib/data/CrowdHuman.py The images in the entire batch are # resize together. batch_augments=[ dict(type='BatchResize', scale=(1400, 800), pad_size_divisor=64) ]), 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, upsample_cfg=dict(mode='bilinear', align_corners=False)), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_generator=dict( type='AnchorGenerator', scales=[8], ratios=[1.0, 2.0, 3.0], strides=[4, 8, 16, 32, 64], centers=[(8, 8), (8, 8), (8, 8), (8, 8), (8, 8)]), 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], clip_border=False), loss_cls=dict(type='CrossEntropyLoss', loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)), roi_head=dict( type='MultiInstanceRoIHead', bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict( type='RoIAlign', output_size=7, sampling_ratio=-1, aligned=True, use_torchvision=True), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=dict( type='MultiInstanceBBoxHead', with_refine=False, num_shared_fcs=2, in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=1, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0., 0., 0., 0.], target_stds=[0.1, 0.1, 0.2, 0.2]), reg_class_agnostic=False, loss_cls=dict( type='CrossEntropyLoss', loss_weight=1.0, use_sigmoid=False, reduction='none'), loss_bbox=dict( type='SmoothL1Loss', loss_weight=1.0, reduction='none'))), # model training and testing settings train_cfg=dict( rpn=dict( assigner=dict( type='MaxIoUAssigner', pos_iou_thr=0.7, neg_iou_thr=(0.3, 0.7), 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=2400, max_per_img=2000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=2), rcnn=dict( assigner=dict( type='MultiInstanceAssigner', pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.3, match_low_quality=False, ignore_iof_thr=-1), sampler=dict( type='MultiInsRandomSampler', num=512, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=False), pos_weight=-1, debug=False)), test_cfg=dict( rpn=dict( nms_pre=1200, max_per_img=1000, nms=dict(type='nms', iou_threshold=0.7), min_bbox_size=2), rcnn=dict( nms=dict(type='nms', iou_threshold=0.5), score_thr=0.01, max_per_img=500))) dataset_type = 'CrowdHumanDataset' data_root = 'data/CrowdHuman/' # Example to use different file client # Method 1: simply set the data root and let the file I/O module # automatically infer from prefix (not support LMDB and Memcache yet) # data_root = 's3://openmmlab/datasets/tracking/CrowdHuman/' # Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6 # backend_args = dict( # backend='petrel', # path_mapping=dict({ # './data/': 's3://openmmlab/datasets/tracking/', # 'data/': 's3://openmmlab/datasets/tracking/' # })) backend_args = None train_pipeline = [ dict(type='LoadImageFromFile', backend_args=backend_args), dict(type='LoadAnnotations', with_bbox=True), dict(type='RandomFlip', prob=0.5), dict( type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'flip', 'flip_direction')) ] test_pipeline = [ dict(type='LoadImageFromFile', backend_args=backend_args), dict(type='Resize', scale=(1400, 800), keep_ratio=True), # avoid bboxes being resized dict(type='LoadAnnotations', with_bbox=True), dict( type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] train_dataloader = dict( batch_size=2, num_workers=4, persistent_workers=True, sampler=dict(type='DefaultSampler', shuffle=True), batch_sampler=None, # The 'batch_sampler' may decrease the precision dataset=dict( type=dataset_type, data_root=data_root, ann_file='annotation_train.odgt', data_prefix=dict(img='Images/'), filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=train_pipeline, backend_args=backend_args)) val_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type='DefaultSampler', shuffle=False), dataset=dict( type=dataset_type, data_root=data_root, ann_file='annotation_val.odgt', data_prefix=dict(img='Images/'), test_mode=True, pipeline=test_pipeline, backend_args=backend_args)) test_dataloader = val_dataloader val_evaluator = dict( type='CrowdHumanMetric', ann_file=data_root + 'annotation_val.odgt', metric=['AP', 'MR', 'JI'], backend_args=backend_args) test_evaluator = val_evaluator train_cfg = dict(type='EpochBasedTrainLoop', max_epochs=30, val_interval=1) val_cfg = dict(type='ValLoop') test_cfg = dict(type='TestLoop') param_scheduler = [ dict( type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=800), dict( type='MultiStepLR', begin=0, end=30, by_epoch=True, milestones=[24, 27], gamma=0.1) ] # optimizer auto_scale_lr = dict(base_batch_size=16) optim_wrapper = dict( type='OptimWrapper', optimizer=dict(type='SGD', lr=0.002, momentum=0.9, weight_decay=0.0001))