models/gpvit/configs/gpvit/mask_rcnn/gpvit_l1_maskrcnn_3x.py [21:205]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - out_indices=(11,), final_norm=False, init_cfg=dict(type='Pretrained', checkpoint=checkpoint_url, prefix="backbone."), convert_syncbn=True), neck=dict( type='FPN', in_channels=[embed_dims, embed_dims, embed_dims, embed_dims], out_channels=256, num_outs=5, norm_cfg=dict(type='SyncBN', requires_grad=True)), 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], 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='Shared4Conv1FCBBoxHead', norm_cfg=dict(type='SyncBN', requires_grad=True), 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.], 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)), mask_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), mask_head=dict( type='FCNMaskHead', num_convs=4, in_channels=256, conv_out_channels=256, num_classes=80, # norm_cfg=dict(type='SyncBN', requires_grad=True), loss_mask=dict( type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))), # model training and testing settings 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=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, 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, mask_thr_binary=0.5))) # optimizer 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='RandomCrop', crop_type='absolute_range', crop_size=(1024, 1024), allow_negative_crop=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( samples_per_gpu=2, workers_per_gpu=2, train=dict(pipeline=train_pipeline)) optimizer = dict( _delete_=True, type='AdamW', lr=0.0002, weight_decay=0.05, paramwise_cfg=dict( custom_keys={ 'level_embed': dict(decay_mult=0.), 'pos_embed': dict(decay_mult=0.), 'norm': dict(decay_mult=0.), 'bias': dict(decay_mult=0.), '.absolute_pos_embed': dict(decay_mult=0.0), '.relative_position_bias_table': dict(decay_mult=0.0), '.pos_embed': dict(decay_mult=0.0), '.group_token': dict(decay_mult=0.0), '.dw_norm': dict(decay_mult=0.0) })) optimizer_config = dict(grad_clip=None) fp16 = dict(loss_scale=dict(init_scale=512)) checkpoint_config = dict( interval=1, max_keep_ckpts=3, save_last=True, ) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - models/gpvit/configs/gpvit/mask_rcnn/gpvit_l3_maskrcnn_3x.py [21:205]: - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - out_indices=(11,), final_norm=False, init_cfg=dict(type='Pretrained', checkpoint=checkpoint_url, prefix="backbone."), convert_syncbn=True), neck=dict( type='FPN', in_channels=[embed_dims, embed_dims, embed_dims, embed_dims], out_channels=256, num_outs=5, norm_cfg=dict(type='SyncBN', requires_grad=True)), 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], 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='Shared4Conv1FCBBoxHead', norm_cfg=dict(type='SyncBN', requires_grad=True), 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.], 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)), mask_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0), out_channels=256, featmap_strides=[4, 8, 16, 32]), mask_head=dict( type='FCNMaskHead', num_convs=4, in_channels=256, conv_out_channels=256, num_classes=80, # norm_cfg=dict(type='SyncBN', requires_grad=True), loss_mask=dict( type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))), # model training and testing settings 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=True, ignore_iof_thr=-1), sampler=dict( type='RandomSampler', num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True), mask_size=28, 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, mask_thr_binary=0.5))) # optimizer 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='RandomCrop', crop_type='absolute_range', crop_size=(1024, 1024), allow_negative_crop=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( samples_per_gpu=2, workers_per_gpu=2, train=dict(pipeline=train_pipeline)) optimizer = dict( _delete_=True, type='AdamW', lr=0.0002, weight_decay=0.05, paramwise_cfg=dict( custom_keys={ 'level_embed': dict(decay_mult=0.), 'pos_embed': dict(decay_mult=0.), 'norm': dict(decay_mult=0.), 'bias': dict(decay_mult=0.), '.absolute_pos_embed': dict(decay_mult=0.0), '.relative_position_bias_table': dict(decay_mult=0.0), '.pos_embed': dict(decay_mult=0.0), '.group_token': dict(decay_mult=0.0), '.dw_norm': dict(decay_mult=0.0) })) optimizer_config = dict(grad_clip=None) fp16 = dict(loss_scale=dict(init_scale=512)) checkpoint_config = dict( interval=1, max_keep_ckpts=3, save_last=True, ) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -