Spaces:
Runtime error
Runtime error
| _base_ = './rtmdet_l_8xb32-300e_coco.py' | |
| model = dict( | |
| bbox_head=dict( | |
| _delete_=True, | |
| type='RTMDetInsSepBNHead', | |
| num_classes=80, | |
| in_channels=256, | |
| stacked_convs=2, | |
| share_conv=True, | |
| pred_kernel_size=1, | |
| feat_channels=256, | |
| act_cfg=dict(type='SiLU', inplace=True), | |
| norm_cfg=dict(type='SyncBN', requires_grad=True), | |
| anchor_generator=dict( | |
| type='MlvlPointGenerator', offset=0, strides=[8, 16, 32]), | |
| bbox_coder=dict(type='DistancePointBBoxCoder'), | |
| loss_cls=dict( | |
| type='QualityFocalLoss', | |
| use_sigmoid=True, | |
| beta=2.0, | |
| loss_weight=1.0), | |
| loss_bbox=dict(type='GIoULoss', loss_weight=2.0), | |
| loss_mask=dict( | |
| type='DiceLoss', loss_weight=2.0, eps=5e-6, reduction='mean')), | |
| test_cfg=dict( | |
| nms_pre=1000, | |
| min_bbox_size=0, | |
| score_thr=0.05, | |
| nms=dict(type='nms', iou_threshold=0.6), | |
| max_per_img=100, | |
| mask_thr_binary=0.5), | |
| ) | |
| train_pipeline = [ | |
| dict( | |
| type='LoadImageFromFile', | |
| file_client_args={{_base_.file_client_args}}), | |
| dict( | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True, | |
| poly2mask=False), | |
| dict(type='CachedMosaic', img_scale=(640, 640), pad_val=114.0), | |
| dict( | |
| type='RandomResize', | |
| scale=(1280, 1280), | |
| ratio_range=(0.1, 2.0), | |
| keep_ratio=True), | |
| dict( | |
| type='RandomCrop', | |
| crop_size=(640, 640), | |
| recompute_bbox=True, | |
| allow_negative_crop=True), | |
| dict(type='YOLOXHSVRandomAug'), | |
| dict(type='RandomFlip', prob=0.5), | |
| dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))), | |
| dict( | |
| type='CachedMixUp', | |
| img_scale=(640, 640), | |
| ratio_range=(1.0, 1.0), | |
| max_cached_images=20, | |
| pad_val=(114, 114, 114)), | |
| dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1)), | |
| dict(type='PackDetInputs') | |
| ] | |
| train_dataloader = dict(pin_memory=True, dataset=dict(pipeline=train_pipeline)) | |
| train_pipeline_stage2 = [ | |
| dict( | |
| type='LoadImageFromFile', | |
| file_client_args={{_base_.file_client_args}}), | |
| dict( | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True, | |
| poly2mask=False), | |
| dict( | |
| type='RandomResize', | |
| scale=(640, 640), | |
| ratio_range=(0.1, 2.0), | |
| keep_ratio=True), | |
| dict( | |
| type='RandomCrop', | |
| crop_size=(640, 640), | |
| recompute_bbox=True, | |
| allow_negative_crop=True), | |
| dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1)), | |
| dict(type='YOLOXHSVRandomAug'), | |
| dict(type='RandomFlip', prob=0.5), | |
| dict(type='Pad', size=(640, 640), pad_val=dict(img=(114, 114, 114))), | |
| dict(type='PackDetInputs') | |
| ] | |
| custom_hooks = [ | |
| dict( | |
| type='EMAHook', | |
| ema_type='ExpMomentumEMA', | |
| momentum=0.0002, | |
| update_buffers=True, | |
| priority=49), | |
| dict( | |
| type='PipelineSwitchHook', | |
| switch_epoch=280, | |
| switch_pipeline=train_pipeline_stage2) | |
| ] | |
| val_evaluator = dict(metric=['bbox', 'segm']) | |
| test_evaluator = val_evaluator | |