Subclass torch's LayerNorm to handle fp16.

多特征融合 AFF

直接相加 DirectAddFuse

多特征融合 iAFF

Computes and stores the average and current value

Computes and stores the average and current value

r"""HTSAT based on the Swin Transformer Args: spec_size (int | tuple(int)): Input Spectrogram size. Default 256 patch_size (int |

MLP as used in Vision Transformer, MLP-Mixer and related networks

Can sample data from audio-text databases Params: sampling_rate: audio sampling rate max_clip_len: max length (seconds) of audio clip to b

A basic Swin Transformer layer for one stage. Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input reso

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

2D Image to Patch Embedding

r"""Swin Transformer Block. Args: dim (int): Number of input channels. input_resolution (tuple[int]): Input resolution. nu

r"""Window based multi-head self attention (W-MSA) module with relative position bias. It supports both of shifted and non-shifted window. Arg

A ResNet class that is similar to torchvision's but contains the following changes: - There are now 3 "stem" convolutions as opposed to 1, wi

r"""Patch Merging Layer. Args: input_resolution (tuple[int]): Resolution of input feature. dim (int): Number of input channels.

timm model adapter # FIXME this adapter is a work in progress, may change in ways that break weight compat