Loading CLCNet/configs/cascade_rcnn_r50_fpn_1x_LHCByCOCO_New0214Cnt56_DetCntReLUV12StgA64StgW01_M2Gpus.py 0 → 100644 +237 −0 Original line number Diff line number Diff line # model settings model = dict( type='CascadeRCNN', num_stages=1, #Fixme: 3==>2 pretrained='torchvision://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, style='pytorch'), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_scales=[8], anchor_ratios=[0.5, 1.0, 2.0], anchor_strides=[4, 8, 16, 32, 64], 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)), bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=[ # dict( # type='SharedFCBBoxHead', # num_fcs=2, # in_channels=256, # fc_out_channels=1024, # roi_feat_size=7, # num_classes=141, # Fixme: 81, ==> 146+1+2. # num_counts=10, # Fixme: 4 # 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='SharedFCBBoxHead', # num_fcs=2, # in_channels=256, # fc_out_channels=1024, # roi_feat_size=7, # num_classes=141, # Fixme: 81, ==> 146+1+2. # num_counts=17, # Fixme: 16 # 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='SharedFCBBoxHead', num_fcs=2, in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=141, # Fixme: 81, ==> 146+1+2. num_counts=64, # Fixme: 64 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)) ]) # 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, min_bbox_size=0), rcnn=[ # 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), # 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), # pos_weight=-1, # debug=False)#, 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), 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, min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100), keep_all_stages=False) #Fixme: dataset settings dataset_type = 'CocoLHCDataset' data_root = '/data1/mmdetection_count/data/LHC/' # data/coco ==> data/LHC 20191014 2024 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), dict(type='Resize', img_scale=(1333,800), keep_ratio=True), # Fixme: img_scale = (1333,800) ==> (800,1333) 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_counts']), #Fixme: + ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333,800), # Fixme: img_scale = (1333,800) ==> (800,1333) 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=6, workers_per_gpu=2, train=dict( type=dataset_type, ann_file=data_root + 'annotations/CommodityDataset_GtTxtsTrain_BsdHand1201N1500ForEASTCnt65_0214Cnt56.json', # CommodityDataset_GtTxtsTrain_BsdHand1201N1500ForEAST_0114 img_prefix=data_root + 'CommodityDataset_ImagesTrain_BsdHand1201N1500/', # pipeline=train_pipeline), val=dict( type=dataset_type, ann_file=data_root + 'annotations/CommodityDataset_GtTxtsTest_BsdHand1201N1500ForEAST_0114.json', img_prefix=data_root + 'CommodityDataset_ImagesTest_BsdHand1201N1500/', pipeline=test_pipeline), test=dict( type=dataset_type, ann_file=data_root + 'annotations/CommodityDataset_GtTxtsTest_BsdHand1201N1500ForEAST_0114.json', img_prefix=data_root + 'CommodityDataset_ImagesTest_BsdHand1201N1500/', pipeline=test_pipeline)) # optimizer optimizer = dict(type='SGD', lr=0.02, 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=[8, 11]) checkpoint_config = dict(interval=1) # yapf:disable log_config = dict( interval=50, hooks=[ dict(type='TextLoggerHook'), # dict(type='TensorboardLoggerHook') ]) # yapf:enable # runtime settings total_epochs = 12 dist_params = dict(backend='nccl') log_level = 'INFO' work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x_LHCByCOCO_New0214Cnt56_DetCntReLUV12StgA64StgW01_M2Gpus' load_from = None resume_from = None workflow = [('train', 1)] Loading
CLCNet/configs/cascade_rcnn_r50_fpn_1x_LHCByCOCO_New0214Cnt56_DetCntReLUV12StgA64StgW01_M2Gpus.py 0 → 100644 +237 −0 Original line number Diff line number Diff line # model settings model = dict( type='CascadeRCNN', num_stages=1, #Fixme: 3==>2 pretrained='torchvision://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, style='pytorch'), neck=dict( type='FPN', in_channels=[256, 512, 1024, 2048], out_channels=256, num_outs=5), rpn_head=dict( type='RPNHead', in_channels=256, feat_channels=256, anchor_scales=[8], anchor_ratios=[0.5, 1.0, 2.0], anchor_strides=[4, 8, 16, 32, 64], 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)), bbox_roi_extractor=dict( type='SingleRoIExtractor', roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2), out_channels=256, featmap_strides=[4, 8, 16, 32]), bbox_head=[ # dict( # type='SharedFCBBoxHead', # num_fcs=2, # in_channels=256, # fc_out_channels=1024, # roi_feat_size=7, # num_classes=141, # Fixme: 81, ==> 146+1+2. # num_counts=10, # Fixme: 4 # 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='SharedFCBBoxHead', # num_fcs=2, # in_channels=256, # fc_out_channels=1024, # roi_feat_size=7, # num_classes=141, # Fixme: 81, ==> 146+1+2. # num_counts=17, # Fixme: 16 # 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='SharedFCBBoxHead', num_fcs=2, in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=141, # Fixme: 81, ==> 146+1+2. num_counts=64, # Fixme: 64 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)) ]) # 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, min_bbox_size=0), rcnn=[ # 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), # 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), # pos_weight=-1, # debug=False)#, 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), 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, min_bbox_size=0), rcnn=dict( score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100), keep_all_stages=False) #Fixme: dataset settings dataset_type = 'CocoLHCDataset' data_root = '/data1/mmdetection_count/data/LHC/' # data/coco ==> data/LHC 20191014 2024 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), dict(type='Resize', img_scale=(1333,800), keep_ratio=True), # Fixme: img_scale = (1333,800) ==> (800,1333) 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_counts']), #Fixme: + ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1333,800), # Fixme: img_scale = (1333,800) ==> (800,1333) 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=6, workers_per_gpu=2, train=dict( type=dataset_type, ann_file=data_root + 'annotations/CommodityDataset_GtTxtsTrain_BsdHand1201N1500ForEASTCnt65_0214Cnt56.json', # CommodityDataset_GtTxtsTrain_BsdHand1201N1500ForEAST_0114 img_prefix=data_root + 'CommodityDataset_ImagesTrain_BsdHand1201N1500/', # pipeline=train_pipeline), val=dict( type=dataset_type, ann_file=data_root + 'annotations/CommodityDataset_GtTxtsTest_BsdHand1201N1500ForEAST_0114.json', img_prefix=data_root + 'CommodityDataset_ImagesTest_BsdHand1201N1500/', pipeline=test_pipeline), test=dict( type=dataset_type, ann_file=data_root + 'annotations/CommodityDataset_GtTxtsTest_BsdHand1201N1500ForEAST_0114.json', img_prefix=data_root + 'CommodityDataset_ImagesTest_BsdHand1201N1500/', pipeline=test_pipeline)) # optimizer optimizer = dict(type='SGD', lr=0.02, 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=[8, 11]) checkpoint_config = dict(interval=1) # yapf:disable log_config = dict( interval=50, hooks=[ dict(type='TextLoggerHook'), # dict(type='TensorboardLoggerHook') ]) # yapf:enable # runtime settings total_epochs = 12 dist_params = dict(backend='nccl') log_level = 'INFO' work_dir = './work_dirs/cascade_rcnn_r50_fpn_1x_LHCByCOCO_New0214Cnt56_DetCntReLUV12StgA64StgW01_M2Gpus' load_from = None resume_from = None workflow = [('train', 1)]
