search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.21k stars 9.4k forks source link

What do "with mask" and "with_semantic_seg" represent in the HTC model？ #972

Closed abing222 closed 5 years ago

abing222 commented 5 years ago

with_mask=True, with_crowd=True, with_label=True, with_semantic_seg=True

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='HTCMaskHead', num_convs=4, in_channels=256, conv_out_channels=256, num_classes=81, 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=2), 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=183, ignore_label=255, loss_weight=0.2))

hellock commented 5 years ago

with_mask and with_semantic_seg correspond to the mask annotation and stuff annotation of COCO dataset.