We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
According to https://github.com/lattice-ai/DeepLabV3-Plus/blob/master/deeplabv3plus/model/backbones.py#L7 you use as your backbone features for resnet50
'feature_1': 'conv4_block6_2_relu',
'feature_2': 'conv2_block3_2_relu'
This would mean that you are using only three out of the four resnet stages, see naming scheme of https://github.com/tensorflow/tensorflow/blob/v2.4.1/tensorflow/python/keras/applications/resnet.py#L468
Is this intended? If so, why?
According to https://github.com/lattice-ai/DeepLabV3-Plus/blob/master/deeplabv3plus/model/backbones.py#L7 you use as your backbone features for resnet50
This would mean that you are using only three out of the four resnet stages, see naming scheme of https://github.com/tensorflow/tensorflow/blob/v2.4.1/tensorflow/python/keras/applications/resnet.py#L468
Is this intended? If so, why?