Conv2d module with customized initialization.

A residual block that can optionally change the number of channels. :param channels: the number of input channels. :param emb_channels: t

A sequential module that passes timestep embeddings to the children that support it as an extra input.

1x1 Conv1d with customized initialization.

An attention block that allows spatial positions to attend to each other. Originally ported from here, but adapted to the N-d case. https

Layer normalization module. :param int nout: output dim size :param int dim: dimension to be normalized

Encoder based on a user-supplied vocabulary (file or list).

Transformer block for image-like data. First, project the input (aka embedding) and reshape to b, t, d. Then apply standard transform

CARDINAL类

A downsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determini

Subclass torch's LayerNorm to handle fp16.

Defines a PatchGAN discriminator as in Pix2Pix --> see https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/models/networks.py

A single linear layer which does a 1x1 conv

多特征融合 AFF

中文数字/数位字符 每个字符除繁简体外还有一个额外的大写字符 e.g. '陆' 和 '陸'

Conv1d module with customized initialization.

直接相加 DirectAddFuse

Frequency-wise normalization

An upsampling layer with an optional convolution. :param channels: channels in the inputs and outputs. :param use_conv: a bool determinin

多特征融合 iAFF

CausalConv1d module with customized initialization.

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

This module produces sinusoidal positional embeddings of any length. Padding symbols are ignored.

This module produces sinusoidal positional embeddings of any length. Padding symbols are ignored.

Implementation of a sine-based periodic activation function Shape: - Input: (B, C, T) - Output: (B, C, T), same shape as the

A modified Snake function which uses separate parameters for the magnitude of the periodic components Shape: - Input: (B, C, T)