Source code for neural_de.transformations.diffusion.unet.qkv_attention

from torch import nn
import torch as th
import math


[docs] class QKVAttention(nn.Module): """ A module which performs QKV attention and splits in a different order. """ def __init__(self, n_heads): super().__init__() self.n_heads = n_heads
[docs] def forward(self, qkv): """ Apply QKV attention. :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor after attention. """ bs, width, length = qkv.shape assert width % (3 * self.n_heads) == 0 ch = width // (3 * self.n_heads) q, k, v = qkv.chunk(3, dim=1) scale = 1 / math.sqrt(math.sqrt(ch)) weight = th.einsum( "bct,bcs->bts", (q * scale).view(bs * self.n_heads, ch, length), (k * scale).view(bs * self.n_heads, ch, length), ) # More stable with f16 than dividing afterwards weight = th.softmax(weight.float(), dim=-1).type(weight.dtype) a = th.einsum("bts,bcs->bct", weight, v.reshape(bs * self.n_heads, ch, length)) return a.reshape(bs, -1, length)