# model settings model = dict( type='CascadeRCNN', # num_stages=3, pretrained='open-mmlab://msra/hrnetv2_w32', backbone=dict( type='HRNet', extra=dict( stage1=dict( num_modules=1, num_branches=1, block='BOTTLENECK', num_blocks=(4, ), num_channels=(64, )), stage2=dict( num_modules=1, num_branches=2, block='BASIC', num_blocks=(4, 4), num_channels=(32, 64)), stage3=dict( num_modules=4, num_branches=3, block='BASIC', num_blocks=(4, 4, 4), num_channels=(32, 64, 128)), stage4=dict( num_modules=3, num_branches=4, block='BASIC', num_blocks=(4, 4, 4, 4), num_channels=(32, 64, 128, 256)))), neck=dict(type='HRFPN', in_channels=[32, 64, 128, 256], out_channels=256), 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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)), roi_head=dict( type='CascadeRoIHead', 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=2), # may conflict out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=[ dict( type='Shared2FCBBoxHead', # num_fcs=2, 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=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', # num_fcs=2, 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=[0.05, 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', # num_fcs=2, 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=[0.033, 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=2), 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, 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, 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, nms=dict(type='nms', iou_threshold=0.7), max_per_img=2000, 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) ], stage_loss_weights=[1, 0.5, 0.25]) test_cfg = dict( rpn=dict( nms_across_levels=False, nms_pre=1000, nms_post=1000, max_num=1000, nms_thr=0.7, nms=dict(type='nms', iou_threshold=0.7), max_per_img=1000, min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100, mask_thr_binary=0.5)) # dataset settings dataset_type = 'CocoDataset' data_root = '/content/drive/My Drive/Mmdetection/' 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), dict(type='Resize', img_scale=(1333, 800), keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), 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']), ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333, 800), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']), ]) ] data = dict( imgs_per_gpu=2, workers_per_gpu=2, train=dict( type=dataset_type, ann_file='/content/drive/My Drive/chunk.json', img_prefix='/content/drive/My Drive/chunk_images/', pipeline=train_pipeline), val=dict( type=dataset_type, ann_file=data_root + 'VOC2007/test.json', img_prefix=data_root + 'VOC2007/Test/', pipeline=test_pipeline), test=dict( type=dataset_type, ann_file=data_root + 'VOC2007/test.json', img_prefix=data_root + 'VOC2007/Test/', pipeline=test_pipeline)) # evaluation = dict(interval=1, metric=['bbox']) # optimizer optimizer = dict(type='SGD', lr=0.0012, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2)) # learning policy lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=1.0 / 3, step=[16, 19]) checkpoint_config = dict(interval=1,create_symlink=False) # yapf:disable log_config = dict( interval=50, hooks=[ dict(type='TextLoggerHook'), # dict(type='TensorboardLoggerHook') ]) # yapf:enable # runtime settings total_epochs = 36 dist_params = dict(backend='nccl') log_level = 'INFO' work_dir = '/content/drive/My Drive/Mmdetection/new_chunk_cascade_mask_rcnn_hrnetv2p_w32_20e' load_from = None resume_from = '/content/drive/My Drive/Mmdetection/new_chunk_cascade_mask_rcnn_hrnetv2p_w32_20e/epoch_30.pth' workflow = [('train', 1)]