halonet-pytorch:本文中tention注意层的实现，为参数有效的视觉主干缩放局部自注意-源码

HaloNet-火炬 本文的注意力层的实现，。 该存储库将仅容纳关注层，而不会包含更多内容。 安装 $ pip install halonet-pytorch 用法 import torch from halonet_pytorch import HaloAttention attn = HaloAttention ( dim = 512 , # dimension of feature map block_size = 8 , # neighborhood block size (feature map must be divisible by this) halo_size = 4 , # halo size (block receptive field) dim_head = 64 , # dimension of