Created
October 26, 2020 02:30
-
-
Save vpeopleonatank/381dea90ee29a1ce33258c846fd6d720 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| dataset_type = 'CocoDataset' | |
| Classes = ('Hand') | |
| data_root = 'data/handdata/' | |
| img_norm_cfg = dict( | |
| mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) | |
| train_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='LoadAnnotations', with_bbox=True, with_mask=True, with_seg=False), | |
| dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), | |
| dict(type='RandomFlip', flip_ratio=0.5), | |
| dict( | |
| type='Normalize', | |
| mean=[123.675, 116.28, 103.53], | |
| std=[58.395, 57.12, 57.375], | |
| to_rgb=True), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='SegRescale', scale_factor=0.125), | |
| dict(type='DefaultFormatBundle'), | |
| dict( | |
| type='Collect', | |
| keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']) | |
| ] | |
| test_pipeline = [ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiScaleFlipAug', | |
| img_scale=(1333, 800), | |
| flip=False, | |
| transforms=[ | |
| dict(type='Resize', keep_ratio=True), | |
| dict(type='RandomFlip', flip_ratio=0.5), | |
| dict( | |
| type='Normalize', | |
| mean=[123.675, 116.28, 103.53], | |
| std=[58.395, 57.12, 57.375], | |
| to_rgb=True), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='ImageToTensor', keys=['img']), | |
| dict(type='Collect', keys=['img']) | |
| ]) | |
| ] | |
| data = dict( | |
| samples_per_gpu=1, | |
| workers_per_gpu=1, | |
| train=dict( | |
| type='CocoDataset', | |
| ann_file='data/handdata/annotations/hand_instances_train.json', | |
| img_prefix='data/handdata/train/', | |
| pipeline=[ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='LoadAnnotations', | |
| with_bbox=True, | |
| with_mask=True, | |
| with_seg=False), | |
| dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), | |
| dict(type='RandomFlip', flip_ratio=0.5), | |
| dict( | |
| type='Normalize', | |
| mean=[123.675, 116.28, 103.53], | |
| std=[58.395, 57.12, 57.375], | |
| to_rgb=True), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='SegRescale', scale_factor=0.125), | |
| dict(type='DefaultFormatBundle'), | |
| dict( | |
| type='Collect', | |
| keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']) | |
| ], | |
| seg_prefix='data/coco/stuffthingmaps/train2017/', | |
| # classes=('Hand') | |
| ), | |
| val=dict( | |
| type='CocoDataset', | |
| ann_file='data/handdata/annotations/hand_instances_test.json', | |
| img_prefix='data/handdata/test/', | |
| pipeline=[ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiScaleFlipAug', | |
| img_scale=(1333, 800), | |
| flip=False, | |
| transforms=[ | |
| dict(type='Resize', keep_ratio=True), | |
| dict(type='RandomFlip', flip_ratio=0.5), | |
| dict( | |
| type='Normalize', | |
| mean=[123.675, 116.28, 103.53], | |
| std=[58.395, 57.12, 57.375], | |
| to_rgb=True), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='ImageToTensor', keys=['img']), | |
| dict(type='Collect', keys=['img']) | |
| ]) | |
| ], | |
| # classes=('Hand') | |
| ), | |
| test=dict( | |
| type='CocoDataset', | |
| ann_file='data/handdata/annotations/hand_instances_test.json', | |
| img_prefix='data/handdata/test/', | |
| pipeline=[ | |
| dict(type='LoadImageFromFile'), | |
| dict( | |
| type='MultiScaleFlipAug', | |
| img_scale=(1333, 800), | |
| flip=False, | |
| transforms=[ | |
| dict(type='Resize', keep_ratio=True), | |
| dict(type='RandomFlip', flip_ratio=0.5), | |
| dict( | |
| type='Normalize', | |
| mean=[123.675, 116.28, 103.53], | |
| std=[58.395, 57.12, 57.375], | |
| to_rgb=True), | |
| dict(type='Pad', size_divisor=32), | |
| dict(type='ImageToTensor', keys=['img']), | |
| dict(type='Collect', keys=['img']) | |
| ]) | |
| ], | |
| # classes=('Hand') | |
| )) | |
| evaluation = dict(metric=['segm']) | |
| 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=[8, 11]) | |
| total_epochs = 12 | |
| checkpoint_config = dict(interval=1) | |
| log_config = dict(interval=50, hooks=[dict(type='TensorboardLoggerHook')]) | |
| dist_params = dict(backend='nccl') | |
| log_level = 'INFO' | |
| load_from = 'https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/v2.0/detectors/detectors_htc_r50_1x_coco/detectors_htc_r50_1x_coco-329b1453.pth' | |
| resume_from = None | |
| workflow = [('train', 1)] | |
| model = dict( | |
| type='HybridTaskCascade', | |
| pretrained='torchvision://resnet50', | |
| backbone=dict( | |
| type='DetectoRS_ResNet', | |
| depth=50, | |
| num_stages=4, | |
| out_indices=(0, 1, 2, 3), | |
| frozen_stages=1, | |
| norm_cfg=dict(type='BN', requires_grad=True), | |
| norm_eval=True, | |
| style='pytorch', | |
| conv_cfg=dict(type='ConvAWS'), | |
| sac=dict(type='SAC', use_deform=True), | |
| stage_with_sac=(False, True, True, True), | |
| output_img=True), | |
| neck=dict( | |
| type='RFP', | |
| in_channels=[256, 512, 1024, 2048], | |
| out_channels=256, | |
| num_outs=5, | |
| rfp_steps=2, | |
| aspp_out_channels=64, | |
| aspp_dilations=(1, 3, 6, 1), | |
| rfp_backbone=dict( | |
| rfp_inplanes=256, | |
| type='DetectoRS_ResNet', | |
| depth=50, | |
| num_stages=4, | |
| out_indices=(0, 1, 2, 3), | |
| frozen_stages=1, | |
| norm_cfg=dict(type='BN', requires_grad=True), | |
| norm_eval=True, | |
| conv_cfg=dict(type='ConvAWS'), | |
| sac=dict(type='SAC', use_deform=True), | |
| stage_with_sac=(False, True, True, True), | |
| pretrained='torchvision://resnet50', | |
| style='pytorch')), | |
| 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='SmoothL1Loss', beta=0.1111111111111111, loss_weight=1.0)), | |
| roi_head=dict( | |
| type='HybridTaskCascadeRoIHead', | |
| interleaved=True, | |
| mask_info_flow=True, | |
| num_stages=3, | |
| stage_loss_weights=[1, 0.5, 0.25], | |
| bbox_roi_extractor=dict( | |
| type='SingleRoIExtractor', | |
| roi_layer=dict(type='RoIAlign', out_size=7, sample_num=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=1, | |
| 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=True, | |
| loss_cls=dict( | |
| type='CrossEntropyLoss', | |
| use_sigmoid=False, | |
| loss_weight=1.0), | |
| loss_bbox=dict(type='SmoothL1Loss', beta=1.0, | |
| loss_weight=1.0)), | |
| dict( | |
| type='Shared2FCBBoxHead', | |
| in_channels=256, | |
| fc_out_channels=1024, | |
| roi_feat_size=7, | |
| num_classes=1, | |
| bbox_coder=dict( | |
| type='DeltaXYWHBBoxCoder', | |
| target_means=[0.0, 0.0, 0.0, 0.0], | |
| target_stds=[0.05, 0.05, 0.1, 0.1]), | |
| reg_class_agnostic=True, | |
| loss_cls=dict( | |
| type='CrossEntropyLoss', | |
| use_sigmoid=False, | |
| loss_weight=1.0), | |
| loss_bbox=dict(type='SmoothL1Loss', beta=1.0, | |
| loss_weight=1.0)), | |
| dict( | |
| type='Shared2FCBBoxHead', | |
| in_channels=256, | |
| fc_out_channels=1024, | |
| roi_feat_size=7, | |
| num_classes=1, | |
| bbox_coder=dict( | |
| type='DeltaXYWHBBoxCoder', | |
| target_means=[0.0, 0.0, 0.0, 0.0], | |
| target_stds=[0.033, 0.033, 0.067, 0.067]), | |
| reg_class_agnostic=True, | |
| loss_cls=dict( | |
| type='CrossEntropyLoss', | |
| use_sigmoid=False, | |
| loss_weight=1.0), | |
| loss_bbox=dict(type='SmoothL1Loss', beta=1.0, loss_weight=1.0)) | |
| ], | |
| mask_roi_extractor=dict( | |
| type='SingleRoIExtractor', | |
| roi_layer=dict(type='RoIAlign', out_size=14, sample_num=0), | |
| out_channels=256, | |
| featmap_strides=[4, 8, 16, 32]), | |
| mask_head=[ | |
| dict( | |
| type='HTCMaskHead', | |
| with_conv_res=False, | |
| num_convs=4, | |
| in_channels=256, | |
| conv_out_channels=256, | |
| num_classes=1, | |
| loss_mask=dict( | |
| type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)), | |
| dict( | |
| type='HTCMaskHead', | |
| num_convs=4, | |
| in_channels=256, | |
| conv_out_channels=256, | |
| num_classes=1, | |
| loss_mask=dict( | |
| type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)), | |
| dict( | |
| type='HTCMaskHead', | |
| num_convs=4, | |
| in_channels=256, | |
| conv_out_channels=256, | |
| num_classes=1, | |
| loss_mask=dict( | |
| type='CrossEntropyLoss', use_mask=True, loss_weight=1.0)) | |
| ], | |
| # semantic_roi_extractor=dict( | |
| # type='SingleRoIExtractor', | |
| # roi_layer=dict(type='RoIAlign', out_size=14, sample_num=0), | |
| # out_channels=256, | |
| # featmap_strides=[8]), | |
| # semantic_head=dict( | |
| # type='FusedSemanticHead', | |
| # num_ins=5, | |
| # fusion_level=1, | |
| # num_convs=4, | |
| # in_channels=256, | |
| # conv_out_channels=256, | |
| # num_classes=1, | |
| # ignore_label=255, | |
| # loss_weight=0.2) | |
| )) | |
| train_cfg = dict( | |
| rpn=dict( | |
| assigner=dict( | |
| type='MaxIoUAssigner', | |
| pos_iou_thr=0.7, | |
| neg_iou_thr=0.3, | |
| min_pos_iou=0.3, | |
| 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=0, | |
| pos_weight=-1, | |
| debug=False), | |
| rpn_proposal=dict( | |
| nms_across_levels=False, | |
| nms_pre=2000, | |
| nms_post=2000, | |
| max_num=2000, | |
| nms_thr=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, | |
| 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), | |
| dict( | |
| assigner=dict( | |
| type='MaxIoUAssigner', | |
| pos_iou_thr=0.6, | |
| neg_iou_thr=0.6, | |
| min_pos_iou=0.6, | |
| 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), | |
| dict( | |
| assigner=dict( | |
| type='MaxIoUAssigner', | |
| pos_iou_thr=0.7, | |
| neg_iou_thr=0.7, | |
| min_pos_iou=0.7, | |
| 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_across_levels=False, | |
| nms_pre=1000, | |
| nms_post=1000, | |
| max_num=1000, | |
| nms_thr=0.7, | |
| min_bbox_size=0), | |
| rcnn=dict( | |
| score_thr=0.001, | |
| nms=dict(type='nms', iou_thr=0.5), | |
| max_per_img=100, | |
| mask_thr_binary=0.5)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment