Spaces:
No application file
No application file
| _backend_args = None | |
| _multiscale_resize_transforms = [ | |
| dict( | |
| _scope_='mmyolo', | |
| transforms=[ | |
| dict(scale=( | |
| 640, | |
| 640, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='LetterResize'), | |
| ], | |
| type='Compose'), | |
| dict( | |
| _scope_='mmyolo', | |
| transforms=[ | |
| dict(scale=( | |
| 320, | |
| 320, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 320, | |
| 320, | |
| ), | |
| type='LetterResize'), | |
| ], | |
| type='Compose'), | |
| dict( | |
| _scope_='mmyolo', | |
| transforms=[ | |
| dict(scale=( | |
| 960, | |
| 960, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 960, | |
| 960, | |
| ), | |
| type='LetterResize'), | |
| ], | |
| type='Compose'), | |
| ] | |
| affine_scale = 0.9 | |
| albu_train_transforms = [ | |
| dict(_scope_='mmyolo', p=0.01, type='Blur'), | |
| dict(_scope_='mmyolo', p=0.01, type='MedianBlur'), | |
| dict(_scope_='mmyolo', p=0.01, type='ToGray'), | |
| dict(_scope_='mmyolo', p=0.01, type='CLAHE'), | |
| ] | |
| backend_args = None | |
| base_lr = 0.0001 | |
| batch_shapes_cfg = None | |
| batch_size = 4 | |
| check_point_interval = 10 | |
| classes = ( | |
| 'person', | |
| 'bicycle', | |
| 'car', | |
| 'motorcycle', | |
| 'airplane', | |
| 'bus', | |
| 'train', | |
| 'truck', | |
| 'boat', | |
| 'traffic light', | |
| 'fire hydrant', | |
| 'stop sign', | |
| 'parking meter', | |
| 'bench', | |
| 'bird', | |
| 'cat', | |
| 'dog', | |
| 'horse', | |
| 'sheep', | |
| 'cow', | |
| 'elephant', | |
| 'bear', | |
| 'zebra', | |
| 'giraffe', | |
| 'backpack', | |
| 'umbrella', | |
| 'handbag', | |
| 'tie', | |
| 'suitcase', | |
| 'frisbee', | |
| 'skis', | |
| 'snowboard', | |
| 'sports ball', | |
| 'kite', | |
| 'baseball bat', | |
| 'baseball glove', | |
| 'skateboard', | |
| 'surfboard', | |
| 'tennis racket', | |
| 'bottle', | |
| 'wine glass', | |
| 'cup', | |
| 'fork', | |
| 'knife', | |
| 'spoon', | |
| 'bowl', | |
| 'banana', | |
| 'apple', | |
| 'sandwich', | |
| 'orange', | |
| 'broccoli', | |
| 'carrot', | |
| 'hot dog', | |
| 'pizza', | |
| 'donut', | |
| 'cake', | |
| 'chair', | |
| 'couch', | |
| 'potted plant', | |
| 'bed', | |
| 'dining table', | |
| 'toilet', | |
| 'tv', | |
| 'laptop', | |
| 'mouse', | |
| 'remote', | |
| 'keyboard', | |
| 'cell phone', | |
| 'microwave', | |
| 'oven', | |
| 'toaster', | |
| 'sink', | |
| 'refrigerator', | |
| 'book', | |
| 'clock', | |
| 'vase', | |
| 'scissors', | |
| 'teddy bear', | |
| 'hair drier', | |
| 'toothbrush', | |
| 'banner', | |
| 'blanket', | |
| 'branch', | |
| 'bridge', | |
| 'building-other', | |
| 'bush', | |
| 'cabinet', | |
| 'cage', | |
| 'cardboard', | |
| 'carpet', | |
| 'ceiling-other', | |
| 'ceiling-tile', | |
| 'cloth', | |
| 'clothes', | |
| 'clouds', | |
| 'counter', | |
| 'cupboard', | |
| 'curtain', | |
| 'desk-stuff', | |
| 'dirt', | |
| 'door-stuff', | |
| 'fence', | |
| 'floor-marble', | |
| 'floor-other', | |
| 'floor-stone', | |
| 'floor-tile', | |
| 'floor-wood', | |
| 'flower', | |
| 'fog', | |
| 'food-other', | |
| 'fruit', | |
| 'furniture-other', | |
| 'grass', | |
| 'gravel', | |
| 'ground-other', | |
| 'hill', | |
| 'house', | |
| 'leaves', | |
| 'light', | |
| 'mat', | |
| 'metal', | |
| 'mirror-stuff', | |
| 'moss', | |
| 'mountain', | |
| 'mud', | |
| 'napkin', | |
| 'net', | |
| 'paper', | |
| 'pavement', | |
| 'pillow', | |
| 'plant-other', | |
| 'plastic', | |
| 'platform', | |
| 'playingfield', | |
| 'railing', | |
| 'railroad', | |
| 'river', | |
| 'road', | |
| 'rock', | |
| 'roof', | |
| 'rug', | |
| 'salad', | |
| 'sand', | |
| 'sea', | |
| 'shelf', | |
| 'sky-other', | |
| 'skyscraper', | |
| 'snow', | |
| 'solid-other', | |
| 'stairs', | |
| 'stone', | |
| 'straw', | |
| 'structural-other', | |
| 'table', | |
| 'tent', | |
| 'textile-other', | |
| 'towel', | |
| 'tree', | |
| 'vegetable', | |
| 'wall-brick', | |
| 'wall-concrete', | |
| 'wall-other', | |
| 'wall-panel', | |
| 'wall-stone', | |
| 'wall-tile', | |
| 'wall-wood', | |
| 'water-other', | |
| 'waterdrops', | |
| 'window-blind', | |
| 'window-other', | |
| 'wood', | |
| ) | |
| close_mosaic_epochs = 10 | |
| copypaste_prob = 0.3 | |
| custom_hooks = [ | |
| dict( | |
| ema_type='ExpMomentumEMA', | |
| momentum=0.0001, | |
| priority=49, | |
| strict_load=False, | |
| type='EMAHook', | |
| update_buffers=True), | |
| dict( | |
| switch_epoch=90, | |
| switch_pipeline=[ | |
| dict( | |
| _scope_='mmyolo', backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| _scope_='mmyolo', | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| dict( | |
| _scope_='mmyolo', | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='YOLOv5KeepRatioResize'), | |
| dict( | |
| _scope_='mmyolo', | |
| allow_scale_up=True, | |
| pad_val=dict(img=114.0), | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='LetterResize'), | |
| dict( | |
| _scope_='mmyolo', | |
| border_val=( | |
| 114, | |
| 114, | |
| 114, | |
| ), | |
| max_aspect_ratio=100, | |
| max_rotate_degree=0.0, | |
| max_shear_degree=0.0, | |
| min_area_ratio=0.01, | |
| scaling_ratio_range=( | |
| 0.09999999999999998, | |
| 1.9, | |
| ), | |
| type='YOLOv5RandomAffine', | |
| use_mask_refine=True), | |
| dict( | |
| _scope_='mmyolo', | |
| keys=[ | |
| 'gt_masks', | |
| ], | |
| type='RemoveDataElement'), | |
| dict( | |
| _scope_='mmyolo', | |
| bbox_params=dict( | |
| format='pascal_voc', | |
| label_fields=[ | |
| 'gt_bboxes_labels', | |
| 'gt_ignore_flags', | |
| ], | |
| type='BboxParams'), | |
| keymap=dict(gt_bboxes='bboxes', img='image'), | |
| transforms=[ | |
| dict(p=0.01, type='Blur'), | |
| dict(p=0.01, type='MedianBlur'), | |
| dict(p=0.01, type='ToGray'), | |
| dict(p=0.01, type='CLAHE'), | |
| ], | |
| type='mmdet.Albu'), | |
| dict(_scope_='mmyolo', type='YOLOv5HSVRandomAug'), | |
| dict(_scope_='mmyolo', prob=0.5, type='mmdet.RandomFlip'), | |
| dict( | |
| _scope_='mmyolo', | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'flip', | |
| 'flip_direction', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ], | |
| type='mmdet.PipelineSwitchHook'), | |
| ] | |
| data_root = '/data/' | |
| dataset_type = 'YOLOv5CocoDataset' | |
| deepen_factor = 1.0 | |
| default_hooks = dict( | |
| checkpoint=dict(interval=10, max_keep_ckpts=1, type='CheckpointHook'), | |
| logger=dict(_scope_='mmyolo', interval=50, type='LoggerHook'), | |
| param_scheduler=dict( | |
| _scope_='mmyolo', | |
| lr_factor=0.1, | |
| max_epochs=100, | |
| scheduler_type='linear', | |
| type='YOLOv5ParamSchedulerHook'), | |
| sampler_seed=dict(_scope_='mmyolo', type='DistSamplerSeedHook'), | |
| timer=dict(_scope_='mmyolo', type='IterTimerHook'), | |
| visualization=dict(_scope_='mmyolo', type='mmdet.DetVisualizationHook')) | |
| default_scope = 'mmyolo' | |
| env_cfg = dict( | |
| cudnn_benchmark=True, | |
| dist_cfg=dict(backend='nccl'), | |
| mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0)) | |
| img_scale = ( | |
| 640, | |
| 640, | |
| ) | |
| img_scales = [ | |
| ( | |
| 640, | |
| 640, | |
| ), | |
| ( | |
| 320, | |
| 320, | |
| ), | |
| ( | |
| 960, | |
| 960, | |
| ), | |
| ] | |
| last_stage_out_channels = 512 | |
| last_transform = [ | |
| dict(_scope_='mmyolo', keys=[ | |
| 'gt_masks', | |
| ], type='RemoveDataElement'), | |
| dict( | |
| _scope_='mmyolo', | |
| bbox_params=dict( | |
| format='pascal_voc', | |
| label_fields=[ | |
| 'gt_bboxes_labels', | |
| 'gt_ignore_flags', | |
| ], | |
| type='BboxParams'), | |
| keymap=dict(gt_bboxes='bboxes', img='image'), | |
| transforms=[ | |
| dict(p=0.01, type='Blur'), | |
| dict(p=0.01, type='MedianBlur'), | |
| dict(p=0.01, type='ToGray'), | |
| dict(p=0.01, type='CLAHE'), | |
| ], | |
| type='mmdet.Albu'), | |
| dict(_scope_='mmyolo', type='YOLOv5HSVRandomAug'), | |
| dict(_scope_='mmyolo', prob=0.5, type='mmdet.RandomFlip'), | |
| dict( | |
| _scope_='mmyolo', | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'flip', | |
| 'flip_direction', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ] | |
| launcher = 'pytorch' | |
| load_from = 'https://download.openmmlab.com/mmyolo/v0/yolov8/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco/yolov8_l_mask-refine_syncbn_fast_8xb16-500e_coco_20230217_120100-5881dec4.pth' | |
| log_level = 'INFO' | |
| log_processor = dict( | |
| _scope_='mmyolo', by_epoch=True, type='LogProcessor', window_size=50) | |
| loss_bbox_weight = 7.5 | |
| loss_cls_weight = 0.5 | |
| loss_dfl_weight = 0.375 | |
| lr_factor = 0.1 | |
| max_aspect_ratio = 100 | |
| max_epochs = 100 | |
| max_keep_ckpts = 2 | |
| metainfo = dict( | |
| classes=( | |
| 'person', | |
| 'bicycle', | |
| 'car', | |
| 'motorcycle', | |
| 'airplane', | |
| 'bus', | |
| 'train', | |
| 'truck', | |
| 'boat', | |
| 'traffic light', | |
| 'fire hydrant', | |
| 'stop sign', | |
| 'parking meter', | |
| 'bench', | |
| 'bird', | |
| 'cat', | |
| 'dog', | |
| 'horse', | |
| 'sheep', | |
| 'cow', | |
| 'elephant', | |
| 'bear', | |
| 'zebra', | |
| 'giraffe', | |
| 'backpack', | |
| 'umbrella', | |
| 'handbag', | |
| 'tie', | |
| 'suitcase', | |
| 'frisbee', | |
| 'skis', | |
| 'snowboard', | |
| 'sports ball', | |
| 'kite', | |
| 'baseball bat', | |
| 'baseball glove', | |
| 'skateboard', | |
| 'surfboard', | |
| 'tennis racket', | |
| 'bottle', | |
| 'wine glass', | |
| 'cup', | |
| 'fork', | |
| 'knife', | |
| 'spoon', | |
| 'bowl', | |
| 'banana', | |
| 'apple', | |
| 'sandwich', | |
| 'orange', | |
| 'broccoli', | |
| 'carrot', | |
| 'hot dog', | |
| 'pizza', | |
| 'donut', | |
| 'cake', | |
| 'chair', | |
| 'couch', | |
| 'potted plant', | |
| 'bed', | |
| 'dining table', | |
| 'toilet', | |
| 'tv', | |
| 'laptop', | |
| 'mouse', | |
| 'remote', | |
| 'keyboard', | |
| 'cell phone', | |
| 'microwave', | |
| 'oven', | |
| 'toaster', | |
| 'sink', | |
| 'refrigerator', | |
| 'book', | |
| 'clock', | |
| 'vase', | |
| 'scissors', | |
| 'teddy bear', | |
| 'hair drier', | |
| 'toothbrush', | |
| 'banner', | |
| 'blanket', | |
| 'branch', | |
| 'bridge', | |
| 'building-other', | |
| 'bush', | |
| 'cabinet', | |
| 'cage', | |
| 'cardboard', | |
| 'carpet', | |
| 'ceiling-other', | |
| 'ceiling-tile', | |
| 'cloth', | |
| 'clothes', | |
| 'clouds', | |
| 'counter', | |
| 'cupboard', | |
| 'curtain', | |
| 'desk-stuff', | |
| 'dirt', | |
| 'door-stuff', | |
| 'fence', | |
| 'floor-marble', | |
| 'floor-other', | |
| 'floor-stone', | |
| 'floor-tile', | |
| 'floor-wood', | |
| 'flower', | |
| 'fog', | |
| 'food-other', | |
| 'fruit', | |
| 'furniture-other', | |
| 'grass', | |
| 'gravel', | |
| 'ground-other', | |
| 'hill', | |
| 'house', | |
| 'leaves', | |
| 'light', | |
| 'mat', | |
| 'metal', | |
| 'mirror-stuff', | |
| 'moss', | |
| 'mountain', | |
| 'mud', | |
| 'napkin', | |
| 'net', | |
| 'paper', | |
| 'pavement', | |
| 'pillow', | |
| 'plant-other', | |
| 'plastic', | |
| 'platform', | |
| 'playingfield', | |
| 'railing', | |
| 'railroad', | |
| 'river', | |
| 'road', | |
| 'rock', | |
| 'roof', | |
| 'rug', | |
| 'salad', | |
| 'sand', | |
| 'sea', | |
| 'shelf', | |
| 'sky-other', | |
| 'skyscraper', | |
| 'snow', | |
| 'solid-other', | |
| 'stairs', | |
| 'stone', | |
| 'straw', | |
| 'structural-other', | |
| 'table', | |
| 'tent', | |
| 'textile-other', | |
| 'towel', | |
| 'tree', | |
| 'vegetable', | |
| 'wall-brick', | |
| 'wall-concrete', | |
| 'wall-other', | |
| 'wall-panel', | |
| 'wall-stone', | |
| 'wall-tile', | |
| 'wall-wood', | |
| 'water-other', | |
| 'waterdrops', | |
| 'window-blind', | |
| 'window-other', | |
| 'wood', | |
| )) | |
| min_area_ratio = 0.01 | |
| mixup_prob = 0.15 | |
| model = dict( | |
| _scope_='mmyolo', | |
| backbone=dict( | |
| act_cfg=dict(inplace=True, type='SiLU'), | |
| arch='P5', | |
| deepen_factor=1.0, | |
| last_stage_out_channels=512, | |
| norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), | |
| type='YOLOv8CSPDarknet', | |
| widen_factor=1.0), | |
| bbox_head=dict( | |
| bbox_coder=dict(type='DistancePointBBoxCoder'), | |
| head_module=dict( | |
| act_cfg=dict(inplace=True, type='SiLU'), | |
| featmap_strides=[ | |
| 8, | |
| 16, | |
| 32, | |
| ], | |
| in_channels=[ | |
| 256, | |
| 512, | |
| 512, | |
| ], | |
| norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), | |
| num_classes=171, | |
| reg_max=16, | |
| type='YOLOv8HeadModule', | |
| widen_factor=1.0), | |
| loss_bbox=dict( | |
| bbox_format='xyxy', | |
| iou_mode='ciou', | |
| loss_weight=7.5, | |
| reduction='sum', | |
| return_iou=False, | |
| type='IoULoss'), | |
| loss_cls=dict( | |
| loss_weight=0.5, | |
| reduction='none', | |
| type='mmdet.CrossEntropyLoss', | |
| use_sigmoid=True), | |
| loss_dfl=dict( | |
| loss_weight=0.375, | |
| reduction='mean', | |
| type='mmdet.DistributionFocalLoss'), | |
| prior_generator=dict( | |
| offset=0.5, strides=[ | |
| 8, | |
| 16, | |
| 32, | |
| ], type='mmdet.MlvlPointGenerator'), | |
| type='YOLOv8Head'), | |
| data_preprocessor=dict( | |
| bgr_to_rgb=True, | |
| mean=[ | |
| 0.0, | |
| 0.0, | |
| 0.0, | |
| ], | |
| std=[ | |
| 255.0, | |
| 255.0, | |
| 255.0, | |
| ], | |
| type='YOLOv5DetDataPreprocessor'), | |
| neck=dict( | |
| act_cfg=dict(inplace=True, type='SiLU'), | |
| deepen_factor=1.0, | |
| in_channels=[ | |
| 256, | |
| 512, | |
| 512, | |
| ], | |
| norm_cfg=dict(eps=0.001, momentum=0.03, type='BN'), | |
| num_csp_blocks=3, | |
| out_channels=[ | |
| 256, | |
| 512, | |
| 512, | |
| ], | |
| type='YOLOv8PAFPN', | |
| widen_factor=1.0), | |
| test_cfg=dict( | |
| max_per_img=300, | |
| multi_label=True, | |
| nms=dict(iou_threshold=0.7, type='nms'), | |
| nms_pre=30000, | |
| score_thr=0.001), | |
| train_cfg=dict( | |
| assigner=dict( | |
| alpha=0.5, | |
| beta=6.0, | |
| eps=1e-09, | |
| num_classes=171, | |
| topk=10, | |
| type='BatchTaskAlignedAssigner', | |
| use_ciou=True)), | |
| type='YOLODetector') | |
| model_test_cfg = dict( | |
| max_per_img=300, | |
| multi_label=True, | |
| nms=dict(_scope_='mmyolo', iou_threshold=0.7, type='nms'), | |
| nms_pre=30000, | |
| score_thr=0.001) | |
| mosaic_affine_transform = [ | |
| dict( | |
| _scope_='mmyolo', | |
| img_scale=( | |
| 640, | |
| 640, | |
| ), | |
| pad_val=114.0, | |
| pre_transform=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| ], | |
| type='Mosaic'), | |
| dict(_scope_='mmyolo', prob=0.3, type='YOLOv5CopyPaste'), | |
| dict( | |
| _scope_='mmyolo', | |
| border=( | |
| -320, | |
| -320, | |
| ), | |
| border_val=( | |
| 114, | |
| 114, | |
| 114, | |
| ), | |
| max_aspect_ratio=100.0, | |
| max_rotate_degree=0.0, | |
| max_shear_degree=0.0, | |
| min_area_ratio=0.01, | |
| scaling_ratio_range=( | |
| 0.09999999999999998, | |
| 1.9, | |
| ), | |
| type='YOLOv5RandomAffine', | |
| use_mask_refine=True), | |
| ] | |
| norm_cfg = dict(_scope_='mmyolo', eps=0.001, momentum=0.03, type='BN') | |
| num_classes = 171 | |
| num_det_layers = 3 | |
| optim_wrapper = dict( | |
| optimizer=dict(lr=0.0001, type='AdamW', weight_decay=0.05), | |
| paramwise_cfg=dict( | |
| bias_decay_mult=0, bypass_duplicate=True, norm_decay_mult=0), | |
| type='OptimWrapper') | |
| param_scheduler = [ | |
| dict(begin=0, by_epoch=True, end=5, start_factor=0.1, type='LinearLR'), | |
| dict( | |
| begin=70, | |
| by_epoch=True, | |
| convert_to_iter_based=True, | |
| end=100, | |
| eta_min=1.0000000000000002e-06, | |
| type='CosineAnnealingLR'), | |
| ] | |
| persistent_workers = True | |
| pre_transform = [ | |
| dict(_scope_='mmyolo', backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| _scope_='mmyolo', | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| ] | |
| resume = False | |
| save_epoch_intervals = 10 | |
| strides = [ | |
| 8, | |
| 16, | |
| 32, | |
| ] | |
| tal_alpha = 0.5 | |
| tal_beta = 6.0 | |
| tal_topk = 10 | |
| test_annot = 'test_coco.json' | |
| test_cfg = dict(_scope_='mmyolo', type='TestLoop') | |
| test_dataloader = dict( | |
| batch_size=4, | |
| dataset=dict( | |
| _scope_='mmyolo', | |
| ann_file='test_coco.json', | |
| batch_shapes_cfg=None, | |
| data_prefix=dict(img='images/'), | |
| data_root='/data/', | |
| metainfo=dict( | |
| classes=( | |
| 'person', | |
| 'bicycle', | |
| 'car', | |
| 'motorcycle', | |
| 'airplane', | |
| 'bus', | |
| 'train', | |
| 'truck', | |
| 'boat', | |
| 'traffic light', | |
| 'fire hydrant', | |
| 'stop sign', | |
| 'parking meter', | |
| 'bench', | |
| 'bird', | |
| 'cat', | |
| 'dog', | |
| 'horse', | |
| 'sheep', | |
| 'cow', | |
| 'elephant', | |
| 'bear', | |
| 'zebra', | |
| 'giraffe', | |
| 'backpack', | |
| 'umbrella', | |
| 'handbag', | |
| 'tie', | |
| 'suitcase', | |
| 'frisbee', | |
| 'skis', | |
| 'snowboard', | |
| 'sports ball', | |
| 'kite', | |
| 'baseball bat', | |
| 'baseball glove', | |
| 'skateboard', | |
| 'surfboard', | |
| 'tennis racket', | |
| 'bottle', | |
| 'wine glass', | |
| 'cup', | |
| 'fork', | |
| 'knife', | |
| 'spoon', | |
| 'bowl', | |
| 'banana', | |
| 'apple', | |
| 'sandwich', | |
| 'orange', | |
| 'broccoli', | |
| 'carrot', | |
| 'hot dog', | |
| 'pizza', | |
| 'donut', | |
| 'cake', | |
| 'chair', | |
| 'couch', | |
| 'potted plant', | |
| 'bed', | |
| 'dining table', | |
| 'toilet', | |
| 'tv', | |
| 'laptop', | |
| 'mouse', | |
| 'remote', | |
| 'keyboard', | |
| 'cell phone', | |
| 'microwave', | |
| 'oven', | |
| 'toaster', | |
| 'sink', | |
| 'refrigerator', | |
| 'book', | |
| 'clock', | |
| 'vase', | |
| 'scissors', | |
| 'teddy bear', | |
| 'hair drier', | |
| 'toothbrush', | |
| 'banner', | |
| 'blanket', | |
| 'branch', | |
| 'bridge', | |
| 'building-other', | |
| 'bush', | |
| 'cabinet', | |
| 'cage', | |
| 'cardboard', | |
| 'carpet', | |
| 'ceiling-other', | |
| 'ceiling-tile', | |
| 'cloth', | |
| 'clothes', | |
| 'clouds', | |
| 'counter', | |
| 'cupboard', | |
| 'curtain', | |
| 'desk-stuff', | |
| 'dirt', | |
| 'door-stuff', | |
| 'fence', | |
| 'floor-marble', | |
| 'floor-other', | |
| 'floor-stone', | |
| 'floor-tile', | |
| 'floor-wood', | |
| 'flower', | |
| 'fog', | |
| 'food-other', | |
| 'fruit', | |
| 'furniture-other', | |
| 'grass', | |
| 'gravel', | |
| 'ground-other', | |
| 'hill', | |
| 'house', | |
| 'leaves', | |
| 'light', | |
| 'mat', | |
| 'metal', | |
| 'mirror-stuff', | |
| 'moss', | |
| 'mountain', | |
| 'mud', | |
| 'napkin', | |
| 'net', | |
| 'paper', | |
| 'pavement', | |
| 'pillow', | |
| 'plant-other', | |
| 'plastic', | |
| 'platform', | |
| 'playingfield', | |
| 'railing', | |
| 'railroad', | |
| 'river', | |
| 'road', | |
| 'rock', | |
| 'roof', | |
| 'rug', | |
| 'salad', | |
| 'sand', | |
| 'sea', | |
| 'shelf', | |
| 'sky-other', | |
| 'skyscraper', | |
| 'snow', | |
| 'solid-other', | |
| 'stairs', | |
| 'stone', | |
| 'straw', | |
| 'structural-other', | |
| 'table', | |
| 'tent', | |
| 'textile-other', | |
| 'towel', | |
| 'tree', | |
| 'vegetable', | |
| 'wall-brick', | |
| 'wall-concrete', | |
| 'wall-other', | |
| 'wall-panel', | |
| 'wall-stone', | |
| 'wall-tile', | |
| 'wall-wood', | |
| 'water-other', | |
| 'waterdrops', | |
| 'window-blind', | |
| 'window-other', | |
| 'wood', | |
| )), | |
| pipeline=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict(scale=( | |
| 640, | |
| 640, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='LetterResize'), | |
| dict(_scope_='mmdet', type='LoadAnnotations', with_bbox=True), | |
| dict( | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'scale_factor', | |
| 'pad_param', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ], | |
| test_mode=True, | |
| type='YOLOv5CocoDataset'), | |
| drop_last=False, | |
| num_workers=3, | |
| persistent_workers=True, | |
| pin_memory=True, | |
| sampler=dict(shuffle=True, type='DefaultSampler')) | |
| test_evaluator = dict( | |
| _scope_='mmyolo', | |
| ann_file='/data/test_coco.json', | |
| metric='bbox', | |
| proposal_nums=( | |
| 100, | |
| 1, | |
| 10, | |
| ), | |
| type='mmdet.CocoMetric') | |
| test_image_folder = 'images/' | |
| test_pipeline = [ | |
| dict(_scope_='mmyolo', backend_args=None, type='LoadImageFromFile'), | |
| dict(_scope_='mmyolo', scale=( | |
| 640, | |
| 640, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| _scope_='mmyolo', | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='LetterResize'), | |
| dict(_scope_='mmdet', type='LoadAnnotations', with_bbox=True), | |
| dict( | |
| _scope_='mmyolo', | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'scale_factor', | |
| 'pad_param', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ] | |
| train_ann_file = 'annotations/instances_train2017.json' | |
| train_annot = 'train_coco.json' | |
| train_batch_size_per_gpu = 16 | |
| train_cfg = dict( | |
| _scope_='mmyolo', | |
| dynamic_intervals=[ | |
| ( | |
| 90, | |
| 1, | |
| ), | |
| ], | |
| max_epochs=100, | |
| type='EpochBasedTrainLoop', | |
| val_interval=1) | |
| train_data_annot_path = '/data/train_coco.json' | |
| train_data_prefix = 'train2017/' | |
| train_dataloader = dict( | |
| batch_size=4, | |
| collate_fn=dict(type='yolov5_collate'), | |
| dataset=dict( | |
| _scope_='mmyolo', | |
| ann_file='train_coco.json', | |
| data_prefix=dict(img='images/'), | |
| data_root='/data/', | |
| filter_cfg=dict(filter_empty_gt=False, min_size=32), | |
| metainfo=dict( | |
| classes=( | |
| 'person', | |
| 'bicycle', | |
| 'car', | |
| 'motorcycle', | |
| 'airplane', | |
| 'bus', | |
| 'train', | |
| 'truck', | |
| 'boat', | |
| 'traffic light', | |
| 'fire hydrant', | |
| 'stop sign', | |
| 'parking meter', | |
| 'bench', | |
| 'bird', | |
| 'cat', | |
| 'dog', | |
| 'horse', | |
| 'sheep', | |
| 'cow', | |
| 'elephant', | |
| 'bear', | |
| 'zebra', | |
| 'giraffe', | |
| 'backpack', | |
| 'umbrella', | |
| 'handbag', | |
| 'tie', | |
| 'suitcase', | |
| 'frisbee', | |
| 'skis', | |
| 'snowboard', | |
| 'sports ball', | |
| 'kite', | |
| 'baseball bat', | |
| 'baseball glove', | |
| 'skateboard', | |
| 'surfboard', | |
| 'tennis racket', | |
| 'bottle', | |
| 'wine glass', | |
| 'cup', | |
| 'fork', | |
| 'knife', | |
| 'spoon', | |
| 'bowl', | |
| 'banana', | |
| 'apple', | |
| 'sandwich', | |
| 'orange', | |
| 'broccoli', | |
| 'carrot', | |
| 'hot dog', | |
| 'pizza', | |
| 'donut', | |
| 'cake', | |
| 'chair', | |
| 'couch', | |
| 'potted plant', | |
| 'bed', | |
| 'dining table', | |
| 'toilet', | |
| 'tv', | |
| 'laptop', | |
| 'mouse', | |
| 'remote', | |
| 'keyboard', | |
| 'cell phone', | |
| 'microwave', | |
| 'oven', | |
| 'toaster', | |
| 'sink', | |
| 'refrigerator', | |
| 'book', | |
| 'clock', | |
| 'vase', | |
| 'scissors', | |
| 'teddy bear', | |
| 'hair drier', | |
| 'toothbrush', | |
| 'banner', | |
| 'blanket', | |
| 'branch', | |
| 'bridge', | |
| 'building-other', | |
| 'bush', | |
| 'cabinet', | |
| 'cage', | |
| 'cardboard', | |
| 'carpet', | |
| 'ceiling-other', | |
| 'ceiling-tile', | |
| 'cloth', | |
| 'clothes', | |
| 'clouds', | |
| 'counter', | |
| 'cupboard', | |
| 'curtain', | |
| 'desk-stuff', | |
| 'dirt', | |
| 'door-stuff', | |
| 'fence', | |
| 'floor-marble', | |
| 'floor-other', | |
| 'floor-stone', | |
| 'floor-tile', | |
| 'floor-wood', | |
| 'flower', | |
| 'fog', | |
| 'food-other', | |
| 'fruit', | |
| 'furniture-other', | |
| 'grass', | |
| 'gravel', | |
| 'ground-other', | |
| 'hill', | |
| 'house', | |
| 'leaves', | |
| 'light', | |
| 'mat', | |
| 'metal', | |
| 'mirror-stuff', | |
| 'moss', | |
| 'mountain', | |
| 'mud', | |
| 'napkin', | |
| 'net', | |
| 'paper', | |
| 'pavement', | |
| 'pillow', | |
| 'plant-other', | |
| 'plastic', | |
| 'platform', | |
| 'playingfield', | |
| 'railing', | |
| 'railroad', | |
| 'river', | |
| 'road', | |
| 'rock', | |
| 'roof', | |
| 'rug', | |
| 'salad', | |
| 'sand', | |
| 'sea', | |
| 'shelf', | |
| 'sky-other', | |
| 'skyscraper', | |
| 'snow', | |
| 'solid-other', | |
| 'stairs', | |
| 'stone', | |
| 'straw', | |
| 'structural-other', | |
| 'table', | |
| 'tent', | |
| 'textile-other', | |
| 'towel', | |
| 'tree', | |
| 'vegetable', | |
| 'wall-brick', | |
| 'wall-concrete', | |
| 'wall-other', | |
| 'wall-panel', | |
| 'wall-stone', | |
| 'wall-tile', | |
| 'wall-wood', | |
| 'water-other', | |
| 'waterdrops', | |
| 'window-blind', | |
| 'window-other', | |
| 'wood', | |
| )), | |
| pipeline=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| dict( | |
| img_scale=( | |
| 640, | |
| 640, | |
| ), | |
| pad_val=114.0, | |
| pre_transform=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| ], | |
| type='Mosaic'), | |
| dict(prob=0.3, type='YOLOv5CopyPaste'), | |
| dict( | |
| border=( | |
| -320, | |
| -320, | |
| ), | |
| border_val=( | |
| 114, | |
| 114, | |
| 114, | |
| ), | |
| max_aspect_ratio=100.0, | |
| max_rotate_degree=0.0, | |
| max_shear_degree=0.0, | |
| min_area_ratio=0.01, | |
| scaling_ratio_range=( | |
| 0.09999999999999998, | |
| 1.9, | |
| ), | |
| type='YOLOv5RandomAffine', | |
| use_mask_refine=True), | |
| dict( | |
| pre_transform=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| dict( | |
| img_scale=( | |
| 640, | |
| 640, | |
| ), | |
| pad_val=114.0, | |
| pre_transform=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| ], | |
| type='Mosaic'), | |
| dict(prob=0.3, type='YOLOv5CopyPaste'), | |
| dict( | |
| border=( | |
| -320, | |
| -320, | |
| ), | |
| border_val=( | |
| 114, | |
| 114, | |
| 114, | |
| ), | |
| max_aspect_ratio=100.0, | |
| max_rotate_degree=0.0, | |
| max_shear_degree=0.0, | |
| min_area_ratio=0.01, | |
| scaling_ratio_range=( | |
| 0.09999999999999998, | |
| 1.9, | |
| ), | |
| type='YOLOv5RandomAffine', | |
| use_mask_refine=True), | |
| ], | |
| prob=0.15, | |
| type='YOLOv5MixUp'), | |
| dict(keys=[ | |
| 'gt_masks', | |
| ], type='RemoveDataElement'), | |
| dict( | |
| bbox_params=dict( | |
| format='pascal_voc', | |
| label_fields=[ | |
| 'gt_bboxes_labels', | |
| 'gt_ignore_flags', | |
| ], | |
| type='BboxParams'), | |
| keymap=dict(gt_bboxes='bboxes', img='image'), | |
| transforms=[ | |
| dict(p=0.01, type='Blur'), | |
| dict(p=0.01, type='MedianBlur'), | |
| dict(p=0.01, type='ToGray'), | |
| dict(p=0.01, type='CLAHE'), | |
| ], | |
| type='mmdet.Albu'), | |
| dict(type='YOLOv5HSVRandomAug'), | |
| dict(prob=0.5, type='mmdet.RandomFlip'), | |
| dict( | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'flip', | |
| 'flip_direction', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ], | |
| type='YOLOv5CocoDataset'), | |
| num_workers=3, | |
| persistent_workers=True, | |
| pin_memory=True, | |
| sampler=dict(shuffle=True, type='DefaultSampler')) | |
| train_image_folder = 'images/' | |
| train_num_workers = 8 | |
| train_pipeline = [ | |
| dict(_scope_='mmyolo', backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| _scope_='mmyolo', | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| dict( | |
| _scope_='mmyolo', | |
| img_scale=( | |
| 640, | |
| 640, | |
| ), | |
| pad_val=114.0, | |
| pre_transform=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| ], | |
| type='Mosaic'), | |
| dict(_scope_='mmyolo', prob=0.3, type='YOLOv5CopyPaste'), | |
| dict( | |
| _scope_='mmyolo', | |
| border=( | |
| -320, | |
| -320, | |
| ), | |
| border_val=( | |
| 114, | |
| 114, | |
| 114, | |
| ), | |
| max_aspect_ratio=100.0, | |
| max_rotate_degree=0.0, | |
| max_shear_degree=0.0, | |
| min_area_ratio=0.01, | |
| scaling_ratio_range=( | |
| 0.09999999999999998, | |
| 1.9, | |
| ), | |
| type='YOLOv5RandomAffine', | |
| use_mask_refine=True), | |
| dict( | |
| _scope_='mmyolo', | |
| pre_transform=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| dict( | |
| img_scale=( | |
| 640, | |
| 640, | |
| ), | |
| pad_val=114.0, | |
| pre_transform=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| ], | |
| type='Mosaic'), | |
| dict(prob=0.3, type='YOLOv5CopyPaste'), | |
| dict( | |
| border=( | |
| -320, | |
| -320, | |
| ), | |
| border_val=( | |
| 114, | |
| 114, | |
| 114, | |
| ), | |
| max_aspect_ratio=100.0, | |
| max_rotate_degree=0.0, | |
| max_shear_degree=0.0, | |
| min_area_ratio=0.01, | |
| scaling_ratio_range=( | |
| 0.09999999999999998, | |
| 1.9, | |
| ), | |
| type='YOLOv5RandomAffine', | |
| use_mask_refine=True), | |
| ], | |
| prob=0.15, | |
| type='YOLOv5MixUp'), | |
| dict(_scope_='mmyolo', keys=[ | |
| 'gt_masks', | |
| ], type='RemoveDataElement'), | |
| dict( | |
| _scope_='mmyolo', | |
| bbox_params=dict( | |
| format='pascal_voc', | |
| label_fields=[ | |
| 'gt_bboxes_labels', | |
| 'gt_ignore_flags', | |
| ], | |
| type='BboxParams'), | |
| keymap=dict(gt_bboxes='bboxes', img='image'), | |
| transforms=[ | |
| dict(p=0.01, type='Blur'), | |
| dict(p=0.01, type='MedianBlur'), | |
| dict(p=0.01, type='ToGray'), | |
| dict(p=0.01, type='CLAHE'), | |
| ], | |
| type='mmdet.Albu'), | |
| dict(_scope_='mmyolo', type='YOLOv5HSVRandomAug'), | |
| dict(_scope_='mmyolo', prob=0.5, type='mmdet.RandomFlip'), | |
| dict( | |
| _scope_='mmyolo', | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'flip', | |
| 'flip_direction', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ] | |
| train_pipeline_stage2 = [ | |
| dict(_scope_='mmyolo', backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| _scope_='mmyolo', | |
| mask2bbox=True, | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True), | |
| dict(_scope_='mmyolo', scale=( | |
| 640, | |
| 640, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| _scope_='mmyolo', | |
| allow_scale_up=True, | |
| pad_val=dict(img=114.0), | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='LetterResize'), | |
| dict( | |
| _scope_='mmyolo', | |
| border_val=( | |
| 114, | |
| 114, | |
| 114, | |
| ), | |
| max_aspect_ratio=100, | |
| max_rotate_degree=0.0, | |
| max_shear_degree=0.0, | |
| min_area_ratio=0.01, | |
| scaling_ratio_range=( | |
| 0.09999999999999998, | |
| 1.9, | |
| ), | |
| type='YOLOv5RandomAffine', | |
| use_mask_refine=True), | |
| dict(_scope_='mmyolo', keys=[ | |
| 'gt_masks', | |
| ], type='RemoveDataElement'), | |
| dict( | |
| _scope_='mmyolo', | |
| bbox_params=dict( | |
| format='pascal_voc', | |
| label_fields=[ | |
| 'gt_bboxes_labels', | |
| 'gt_ignore_flags', | |
| ], | |
| type='BboxParams'), | |
| keymap=dict(gt_bboxes='bboxes', img='image'), | |
| transforms=[ | |
| dict(p=0.01, type='Blur'), | |
| dict(p=0.01, type='MedianBlur'), | |
| dict(p=0.01, type='ToGray'), | |
| dict(p=0.01, type='CLAHE'), | |
| ], | |
| type='mmdet.Albu'), | |
| dict(_scope_='mmyolo', type='YOLOv5HSVRandomAug'), | |
| dict(_scope_='mmyolo', prob=0.5, type='mmdet.RandomFlip'), | |
| dict( | |
| _scope_='mmyolo', | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'flip', | |
| 'flip_direction', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ] | |
| tta_model = dict( | |
| _scope_='mmyolo', | |
| tta_cfg=dict(max_per_img=300, nms=dict(iou_threshold=0.65, type='nms')), | |
| type='mmdet.DetTTAModel') | |
| tta_pipeline = [ | |
| dict(_scope_='mmyolo', backend_args=None, type='LoadImageFromFile'), | |
| dict( | |
| _scope_='mmyolo', | |
| transforms=[ | |
| [ | |
| dict( | |
| transforms=[ | |
| dict(scale=( | |
| 640, | |
| 640, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='LetterResize'), | |
| ], | |
| type='Compose'), | |
| dict( | |
| transforms=[ | |
| dict(scale=( | |
| 320, | |
| 320, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 320, | |
| 320, | |
| ), | |
| type='LetterResize'), | |
| ], | |
| type='Compose'), | |
| dict( | |
| transforms=[ | |
| dict(scale=( | |
| 960, | |
| 960, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 960, | |
| 960, | |
| ), | |
| type='LetterResize'), | |
| ], | |
| type='Compose'), | |
| ], | |
| [ | |
| dict(prob=1.0, type='mmdet.RandomFlip'), | |
| dict(prob=0.0, type='mmdet.RandomFlip'), | |
| ], | |
| [ | |
| dict(type='mmdet.LoadAnnotations', with_bbox=True), | |
| ], | |
| [ | |
| dict( | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'scale_factor', | |
| 'pad_param', | |
| 'flip', | |
| 'flip_direction', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ], | |
| ], | |
| type='TestTimeAug'), | |
| ] | |
| use_mask2refine = True | |
| val_ann_file = 'annotations/instances_val2017.json' | |
| val_annot = 'test_coco.json' | |
| val_batch_size_per_gpu = 1 | |
| val_cfg = dict(_scope_='mmyolo', type='ValLoop') | |
| val_data_prefix = 'val2017/' | |
| val_dataloader = dict( | |
| batch_size=4, | |
| dataset=dict( | |
| _scope_='mmyolo', | |
| ann_file='test_coco.json', | |
| batch_shapes_cfg=None, | |
| data_prefix=dict(img='images/'), | |
| data_root='/data/', | |
| metainfo=dict( | |
| classes=( | |
| 'person', | |
| 'bicycle', | |
| 'car', | |
| 'motorcycle', | |
| 'airplane', | |
| 'bus', | |
| 'train', | |
| 'truck', | |
| 'boat', | |
| 'traffic light', | |
| 'fire hydrant', | |
| 'stop sign', | |
| 'parking meter', | |
| 'bench', | |
| 'bird', | |
| 'cat', | |
| 'dog', | |
| 'horse', | |
| 'sheep', | |
| 'cow', | |
| 'elephant', | |
| 'bear', | |
| 'zebra', | |
| 'giraffe', | |
| 'backpack', | |
| 'umbrella', | |
| 'handbag', | |
| 'tie', | |
| 'suitcase', | |
| 'frisbee', | |
| 'skis', | |
| 'snowboard', | |
| 'sports ball', | |
| 'kite', | |
| 'baseball bat', | |
| 'baseball glove', | |
| 'skateboard', | |
| 'surfboard', | |
| 'tennis racket', | |
| 'bottle', | |
| 'wine glass', | |
| 'cup', | |
| 'fork', | |
| 'knife', | |
| 'spoon', | |
| 'bowl', | |
| 'banana', | |
| 'apple', | |
| 'sandwich', | |
| 'orange', | |
| 'broccoli', | |
| 'carrot', | |
| 'hot dog', | |
| 'pizza', | |
| 'donut', | |
| 'cake', | |
| 'chair', | |
| 'couch', | |
| 'potted plant', | |
| 'bed', | |
| 'dining table', | |
| 'toilet', | |
| 'tv', | |
| 'laptop', | |
| 'mouse', | |
| 'remote', | |
| 'keyboard', | |
| 'cell phone', | |
| 'microwave', | |
| 'oven', | |
| 'toaster', | |
| 'sink', | |
| 'refrigerator', | |
| 'book', | |
| 'clock', | |
| 'vase', | |
| 'scissors', | |
| 'teddy bear', | |
| 'hair drier', | |
| 'toothbrush', | |
| 'banner', | |
| 'blanket', | |
| 'branch', | |
| 'bridge', | |
| 'building-other', | |
| 'bush', | |
| 'cabinet', | |
| 'cage', | |
| 'cardboard', | |
| 'carpet', | |
| 'ceiling-other', | |
| 'ceiling-tile', | |
| 'cloth', | |
| 'clothes', | |
| 'clouds', | |
| 'counter', | |
| 'cupboard', | |
| 'curtain', | |
| 'desk-stuff', | |
| 'dirt', | |
| 'door-stuff', | |
| 'fence', | |
| 'floor-marble', | |
| 'floor-other', | |
| 'floor-stone', | |
| 'floor-tile', | |
| 'floor-wood', | |
| 'flower', | |
| 'fog', | |
| 'food-other', | |
| 'fruit', | |
| 'furniture-other', | |
| 'grass', | |
| 'gravel', | |
| 'ground-other', | |
| 'hill', | |
| 'house', | |
| 'leaves', | |
| 'light', | |
| 'mat', | |
| 'metal', | |
| 'mirror-stuff', | |
| 'moss', | |
| 'mountain', | |
| 'mud', | |
| 'napkin', | |
| 'net', | |
| 'paper', | |
| 'pavement', | |
| 'pillow', | |
| 'plant-other', | |
| 'plastic', | |
| 'platform', | |
| 'playingfield', | |
| 'railing', | |
| 'railroad', | |
| 'river', | |
| 'road', | |
| 'rock', | |
| 'roof', | |
| 'rug', | |
| 'salad', | |
| 'sand', | |
| 'sea', | |
| 'shelf', | |
| 'sky-other', | |
| 'skyscraper', | |
| 'snow', | |
| 'solid-other', | |
| 'stairs', | |
| 'stone', | |
| 'straw', | |
| 'structural-other', | |
| 'table', | |
| 'tent', | |
| 'textile-other', | |
| 'towel', | |
| 'tree', | |
| 'vegetable', | |
| 'wall-brick', | |
| 'wall-concrete', | |
| 'wall-other', | |
| 'wall-panel', | |
| 'wall-stone', | |
| 'wall-tile', | |
| 'wall-wood', | |
| 'water-other', | |
| 'waterdrops', | |
| 'window-blind', | |
| 'window-other', | |
| 'wood', | |
| )), | |
| pipeline=[ | |
| dict(backend_args=None, type='LoadImageFromFile'), | |
| dict(scale=( | |
| 640, | |
| 640, | |
| ), type='YOLOv5KeepRatioResize'), | |
| dict( | |
| allow_scale_up=False, | |
| pad_val=dict(img=114), | |
| scale=( | |
| 640, | |
| 640, | |
| ), | |
| type='LetterResize'), | |
| dict(_scope_='mmdet', type='LoadAnnotations', with_bbox=True), | |
| dict( | |
| meta_keys=( | |
| 'img_id', | |
| 'img_path', | |
| 'ori_shape', | |
| 'img_shape', | |
| 'scale_factor', | |
| 'pad_param', | |
| ), | |
| type='mmdet.PackDetInputs'), | |
| ], | |
| test_mode=True, | |
| type='YOLOv5CocoDataset'), | |
| drop_last=False, | |
| num_workers=3, | |
| persistent_workers=True, | |
| pin_memory=True, | |
| sampler=dict(shuffle=True, type='DefaultSampler')) | |
| val_evaluator = dict( | |
| _scope_='mmyolo', | |
| ann_file='/data/test_coco.json', | |
| metric='bbox', | |
| proposal_nums=( | |
| 100, | |
| 1, | |
| 10, | |
| ), | |
| type='mmdet.CocoMetric') | |
| val_image_folder = 'images/' | |
| val_interval = 1 | |
| val_interval_stage2 = 1 | |
| val_num_workers = 2 | |
| vis_backends = [ | |
| dict(_scope_='mmyolo', type='LocalVisBackend'), | |
| ] | |
| visualizer = dict( | |
| _scope_='mmyolo', | |
| name='visualizer', | |
| type='mmdet.DetLocalVisualizer', | |
| vis_backends=[ | |
| dict(type='LocalVisBackend'), | |
| ]) | |
| warmup_epochs = 5 | |
| weight_decay = 0.0005 | |
| widen_factor = 1.0 | |
| work_dir = '/out' | |