| checkpoint_config = dict(interval=1) | |
| log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) | |
| custom_hooks = [dict(type='NumClassCheckHook')] | |
| dist_params = dict(backend='nccl') | |
| log_level = 'INFO' | |
| load_from = None | |
| resume_from = None | |
| workflow = [('train', 1)] | |
| opencv_num_threads = 0 | |
| mp_start_method = 'fork' | |
| auto_scale_lr = dict(enable=False, base_batch_size=16) | |
| dataset_type = 'CocoDataset' | |
| data_root = 'data/coco/' | |
| img_norm_cfg = dict( | |
| mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) | |
| train_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict(type='LoadAnnotations', with_bbox=True), | |
| dict( | |
| type='Resize', | |
| img_scale=[(1333, 640), (1333, 800)], | |
| multiscale_mode='range', | |
| keep_ratio=True), | |
| dict(type='RandomFlip', flip_ratio=0.5), | |
| dict( | |
| type='Normalize', | |
| mean=[103.53, 116.28, 123.675], | |
| std=[1.0, 1.0, 1.0], | |
| to_rgb=False), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='DefaultFormatBundle'), | |
| dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) | |
| ] | |
| test_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiScaleFlipAug', | |
| img_scale=(1333, 800), | |
| flip=False, | |
| transforms=[ | |
| dict(type='Resize', keep_ratio=True), | |
| dict(type='RandomFlip'), | |
| dict( | |
| type='Normalize', | |
| mean=[103.53, 116.28, 123.675], | |
| std=[1.0, 1.0, 1.0], | |
| to_rgb=False), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='ImageToTensor', keys=['img']), | |
| dict(type='Collect', keys=['img']) | |
| ]) | |
| ] | |
| data = dict( | |
| samples_per_gpu=2, | |
| workers_per_gpu=2, | |
| train=dict( | |
| type='RepeatDataset', | |
| times=3, | |
| dataset=dict( | |
| type='CocoDataset', | |
| ann_file='data/coco/annotations/instances_train2017.json', | |
| img_prefix='data/coco/train2017/', | |
| pipeline=[ | |
| dict(type='LoadImageFromFile'), | |
| dict(type='LoadAnnotations', with_bbox=True), | |
| dict( | |
| type='Resize', | |
| img_scale=[(1333, 640), (1333, 800)], | |
| multiscale_mode='range', | |
| keep_ratio=True), | |
| dict(type='RandomFlip', flip_ratio=0.5), | |
| dict( | |
| type='Normalize', | |
| mean=[103.53, 116.28, 123.675], | |
| std=[1.0, 1.0, 1.0], | |
| to_rgb=False), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='DefaultFormatBundle'), | |
| dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) | |
| ])), | |
| val=dict( | |
| type='CocoDataset', | |
| ann_file='data/coco/annotations/instances_val2017.json', | |
| img_prefix='data/coco/val2017/', | |
| pipeline=[ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiScaleFlipAug', | |
| img_scale=(1333, 800), | |
| flip=False, | |
| transforms=[ | |
| dict(type='Resize', keep_ratio=True), | |
| dict(type='RandomFlip'), | |
| dict( | |
| type='Normalize', | |
| mean=[103.53, 116.28, 123.675], | |
| std=[1.0, 1.0, 1.0], | |
| to_rgb=False), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='ImageToTensor', keys=['img']), | |
| dict(type='Collect', keys=['img']) | |
| ]) | |
| ]), | |
| test=dict( | |
| type='CocoDataset', | |
| ann_file='data/coco/annotations/instances_val2017.json', | |
| img_prefix='data/coco/val2017/', | |
| pipeline=[ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiScaleFlipAug', | |
| img_scale=(1333, 800), | |
| flip=False, | |
| transforms=[ | |
| dict(type='Resize', keep_ratio=True), | |
| dict(type='RandomFlip'), | |
| dict( | |
| type='Normalize', | |
| mean=[103.53, 116.28, 123.675], | |
| std=[1.0, 1.0, 1.0], | |
| to_rgb=False), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='ImageToTensor', keys=['img']), | |
| dict(type='Collect', keys=['img']) | |
| ]) | |
| ])) | |
| evaluation = dict(interval=1, metric='bbox') | |
| optimizer = dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001) | |
| optimizer_config = dict(grad_clip=None) | |
| lr_config = dict( | |
| policy='step', | |
| warmup='linear', | |
| warmup_iters=500, | |
| warmup_ratio=0.001, | |
| step=[9, 11]) | |
| runner = dict(type='EpochBasedRunner', max_epochs=12) | |
| model = dict( | |
| type='FasterRCNN', | |
| 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=False), | |
| norm_eval=True, | |
| style='caffe', | |
| init_cfg=dict( | |
| type='Pretrained', | |
| checkpoint='open-mmlab://detectron2/resnet50_caffe')), | |
| 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=80, | |
| 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)), | |
| 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=False, | |
| ignore_iof_thr=-1), | |
| sampler=dict( | |
| type='RandomSampler', | |
| num=512, | |
| pos_fraction=0.25, | |
| neg_pos_ub=-1, | |
| add_gt_as_proposals=True), | |
| pos_weight=-1, | |
| debug=False), | |
| test_cfg=dict( | |
| score_thr=0.05, | |
| nms=dict(type='nms', iou_threshold=0.5), | |
| max_per_img=100), | |
| pretrained=None), | |
| train_cfg=dict( | |
| rpn=dict( | |
| assigner=dict( | |
| type='MaxIoUAssigner', | |
| pos_iou_thr=0.7, | |
| neg_iou_thr=0.3, | |
| min_pos_iou=0.3, | |
| match_low_quality=True, | |
| ignore_iof_thr=-1), | |
| sampler=dict( | |
| type='RandomSampler', | |
| num=256, | |
| pos_fraction=0.5, | |
| neg_pos_ub=-1, | |
| add_gt_as_proposals=False), | |
| allowed_border=-1, | |
| pos_weight=-1, | |
| debug=False), | |
| rpn_proposal=dict( | |
| nms_pre=2000, | |
| max_per_img=1000, | |
| nms=dict(type='nms', iou_threshold=0.7), | |
| min_bbox_size=0), | |
| rcnn=dict( | |
| assigner=dict( | |
| type='MaxIoUAssigner', | |
| pos_iou_thr=0.5, | |
| neg_iou_thr=0.5, | |
| min_pos_iou=0.5, | |
| match_low_quality=False, | |
| ignore_iof_thr=-1), | |
| sampler=dict( | |
| type='RandomSampler', | |
| num=512, | |
| pos_fraction=0.25, | |
| neg_pos_ub=-1, | |
| add_gt_as_proposals=True), | |
| pos_weight=-1, | |
| debug=False)), | |
| test_cfg=dict( | |
| rpn=dict( | |
| nms_pre=1000, | |
| max_per_img=1000, | |
| nms=dict(type='nms', iou_threshold=0.7), | |
| min_bbox_size=0), | |
| rcnn=dict( | |
| score_thr=0.05, | |
| nms=dict(type='nms', iou_threshold=0.5), | |
| max_per_img=100))) | |