Open 584669 opened 4 years ago
model = dict( type='CascadeRCNN', num_stages=3, pretrained='torchvision://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, style='pytorch', dcn=dict( modulated=False, deformable_groups=1, fallback_on_stride=False), stage_with_dcn=(False, True, True, True), ),
I used the default setting in mmdetection. According to my experience , frozen the first stage can achieve better results.
model = dict( type='CascadeRCNN', num_stages=3, pretrained='torchvision://resnet50', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(0, 1, 2, 3), frozen_stages=1, style='pytorch', dcn=dict( modulated=False, deformable_groups=1, fallback_on_stride=False), stage_with_dcn=(False, True, True, True), ),