How to modify the number of bounding boxes in Faster-RCNN?

[zz7379]

I am applying the Faster-RCNN to detect the spots on tongue images. There a more than 200 spots on a tongue. How can i modify the number of bounding boxes in Faster-RCNN at test time? Following is my config

model = dict( type='FasterRCNN', pretrained='torchvision://resnet50', backbone=dict( type='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'), 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_generator=dict( type='AnchorGenerator', scales=[2], 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='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='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=False, loss_cls=dict( type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type='L1Loss', loss_weight=1.0)))) 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_across_levels=False, nms_pre=2000, nms_post=1000, max_num=1000, 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, match_low_quality=False, 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)) test_cfg = dict( rpn=dict( nms_across_levels=False, nms_pre=1000, nms_post=1000, max_num=1000, nms_thr=0.6, min_bbox_size=0, max_per_img=1000), rcnn=dict( score_thr=0.01, nms=dict(type='nms', iou_threshold=0.5), max_per_img=200)) dataset_type = 'COCODataset' data_root = 'data/tongue_det/' img_norm_cfg = dict( mean=[83.29629487, 90.69917992, 113.06523135], std=[8.24062785, 8.761491, 9.34409553], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(type='Resize', img_scale=(1536, 1152), 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='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1536, 1152), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), 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/tongue_det/annotations/instances_train.json', img_prefix='data/tongue_det/train/', pipeline=[ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict(type='Resize', img_scale=(1536, 1152), 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='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']) ], classes=('1', )), val=dict( type='CocoDataset', ann_file='data/tongue_det/annotations/instances_val.json', img_prefix='data/tongue_det/val/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1536, 1152), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), 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=('1', )), test=dict( type='CocoDataset', ann_file='data/tongue_det/annotations/instances_val.json', img_prefix='data/tongue_det/val/', pipeline=[ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(1536, 1152), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), 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=('1', ))) evaluation = dict(interval=10, metric='bbox') optimizer = dict(type='SGD', lr=0.025, 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=[16, 22]) total_epochs = 20 checkpoint_config = dict(interval=20) log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = '/home/whw/mmdetection-2.7.0/checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth' resume_from = None workflow = [('train', 1)] resolution_multiplier = 2 classes = ('1', ) gpu_ids = range(0, 1) work_dir = './work_dirs/tongue_det_scale_reshape'

[BIGWangYuDong]

test_cfg = dict( rpn=dict( nms_across_levels=False, nms_pre=1000, nms_post=1000, max_num=1000, nms_thr=0.6, min_bbox_size=0, max_per_img=1000), rcnn=dict( score_thr=0.01, nms=dict(type='nms', iou_threshold=0.5), max_per_img=200))

You can change max_per_img, more details can refer to https://mmdetection.readthedocs.io/en/latest/tutorials/config.html#an-example-of-mask-r-cnn

[zz7379]

Thank you for your patience ,but it is still not working. I set the max_per_img to 200, trained the model and tested it by demo/image_demo.py. The length of "inference_detector(model, img_pth)" is still 100. @BIGWangYuDong