The RetinaNet model is based on the FCOS: Fully Convolutional One-Stage Object Detection paper.
The detection module is in Beta stage, and backward compatibility is not guaranteed.
The following model builders can be used to instantiate a FCOS model, with or
without pre-trained weights. All the model buidlers internally rely on the
torchvision.models.detection.fcos.FCOS base class. Please refer to the source code for
more details about this class.
Constructs a FCOS model with a ResNet-50-FPN backbone.