Module that adds FPN on top of a list of feature maps. The feature maps are currently supposed to be in increasing depth order, and must

Swin Transformer backbone. This backbone is the implementation of `Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Applies padding to input (if needed) so that input can get fully covered by filter you specified. It support two modes "same" and "corner". The

F-S Relation module in CVPR 2020 paper "Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remo

Image to Patch Embedding. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default: 3

Merge patch feature map. This layer groups feature map by kernel_size, and applies norm and linear layers to the grouped feature map. Our impl

Shifted Window Multihead Self-Attention Module. Args: embed_dims (int): Number of input channels. num_heads (int): Number of atten

Args: embed_dims (int): The feature dimension. num_heads (int): Parallel attention heads. feedforward_channels (int): The

Implements one stage in Swin Transformer. Args: embed_dims (int): The feature dimension. num_heads (int): Parallel attention heads

Window based multi-head self-attention (W-MSA) module with relative position bias. Args: embed_dims (int): Number of input channels.

This module is used in RetinaNet to generate extra layers, P6 and P7.