object_detection/configs/convnext/cascade_mask_rcnn_convnext_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco_in1k.py [21:130]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - layer_scale_init_value=1.0, out_indices=[0, 1, 2, 3], ), neck=dict(in_channels=[128, 256, 512, 1024]), roi_head=dict( bbox_head=[ dict( type='ConvFCBBoxHead', num_shared_convs=4, num_shared_fcs=1, in_channels=256, conv_out_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=80, 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, reg_decoded_bbox=True, norm_cfg=dict(type='SyncBN', requires_grad=True), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='GIoULoss', loss_weight=10.0)), dict( type='ConvFCBBoxHead', num_shared_convs=4, num_shared_fcs=1, in_channels=256, conv_out_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=80, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0., 0., 0., 0.], target_stds=[0.05, 0.05, 0.1, 0.1]), reg_class_agnostic=False, reg_decoded_bbox=True, norm_cfg=dict(type='SyncBN', requires_grad=True), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='GIoULoss', loss_weight=10.0)), dict( type='ConvFCBBoxHead', num_shared_convs=4, num_shared_fcs=1, in_channels=256, conv_out_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=80, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0., 0., 0., 0.], target_stds=[0.033, 0.033, 0.067, 0.067]), reg_class_agnostic=False, reg_decoded_bbox=True, norm_cfg=dict(type='SyncBN', requires_grad=True), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='GIoULoss', loss_weight=10.0)) ])) img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) # augmentation strategy originates from DETR / Sparse RCNN train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='RandomFlip', flip_ratio=0.5), dict(type='AutoAugment', policies=[ [ dict(type='Resize', img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], multiscale_mode='value', keep_ratio=True) ], [ dict(type='Resize', img_scale=[(400, 1333), (500, 1333), (600, 1333)], multiscale_mode='value', keep_ratio=True), dict(type='RandomCrop', crop_type='absolute_range', crop_size=(384, 600), allow_negative_crop=True), dict(type='Resize', img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], multiscale_mode='value', override=True, keep_ratio=True) ] ]), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']), ] data = dict(train=dict(pipeline=train_pipeline)) optimizer = dict(constructor='LearningRateDecayOptimizerConstructor', _delete_=True, type='AdamW', - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - object_detection/configs/convnext/cascade_mask_rcnn_convnext_base_patch4_window7_mstrain_480-800_giou_4conv1f_adamw_3x_coco_in22k.py [21:130]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - layer_scale_init_value=1.0, out_indices=[0, 1, 2, 3], ), neck=dict(in_channels=[128, 256, 512, 1024]), roi_head=dict( bbox_head=[ dict( type='ConvFCBBoxHead', num_shared_convs=4, num_shared_fcs=1, in_channels=256, conv_out_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=80, 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, reg_decoded_bbox=True, norm_cfg=dict(type='SyncBN', requires_grad=True), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='GIoULoss', loss_weight=10.0)), dict( type='ConvFCBBoxHead', num_shared_convs=4, num_shared_fcs=1, in_channels=256, conv_out_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=80, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0., 0., 0., 0.], target_stds=[0.05, 0.05, 0.1, 0.1]), reg_class_agnostic=False, reg_decoded_bbox=True, norm_cfg=dict(type='SyncBN', requires_grad=True), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='GIoULoss', loss_weight=10.0)), dict( type='ConvFCBBoxHead', num_shared_convs=4, num_shared_fcs=1, in_channels=256, conv_out_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=80, bbox_coder=dict( type='DeltaXYWHBBoxCoder', target_means=[0., 0., 0., 0.], target_stds=[0.033, 0.033, 0.067, 0.067]), reg_class_agnostic=False, reg_decoded_bbox=True, norm_cfg=dict(type='SyncBN', requires_grad=True), loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='GIoULoss', loss_weight=10.0)) ])) img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) # augmentation strategy originates from DETR / Sparse RCNN train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='RandomFlip', flip_ratio=0.5), dict(type='AutoAugment', policies=[ [ dict(type='Resize', img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], multiscale_mode='value', keep_ratio=True) ], [ dict(type='Resize', img_scale=[(400, 1333), (500, 1333), (600, 1333)], multiscale_mode='value', keep_ratio=True), dict(type='RandomCrop', crop_type='absolute_range', crop_size=(384, 600), allow_negative_crop=True), dict(type='Resize', img_scale=[(480, 1333), (512, 1333), (544, 1333), (576, 1333), (608, 1333), (640, 1333), (672, 1333), (704, 1333), (736, 1333), (768, 1333), (800, 1333)], multiscale_mode='value', override=True, keep_ratio=True) ] ]), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']), ] data = dict(train=dict(pipeline=train_pipeline)) optimizer = dict(constructor='LearningRateDecayOptimizerConstructor', _delete_=True, type='AdamW', - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -