the question of featmap_strides in roi_head

[liuyanzhi1214]

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='FocalLoss', use_sigmoid=True, gamma=2, alpha=0.25, loss_weight=1.0), loss_bbox=dict(type='SmoothL1Loss', beta=1.0, 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', in_channels=256, fc_out_channels=1024, roi_feat_size=7, num_classes=2, 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='SmoothL1Loss', beta=1.0, loss_weight=1.0), conv_out_channels=256, norm_cfg=dict(type='BN', requires_grad=True)))) the FPN output 5 level(p2-p6),why there are only 4 level be uesd in roi_extractor?

[hhaAndroid]

@liuyanzhi1214 hi, You can refer to the FPN

[ZwwWayne]

The implementation follows the description and official code release of FPN. The issue is closed as the question seems to be answered. Feel free to reopen it if you have any further questions.