|
import math
|
|
|
|
import torch
|
|
import torch.nn as nn
|
|
from diffusers.models.modeling_utils import ModelMixin
|
|
from einops import rearrange
|
|
from einops.layers.torch import Rearrange
|
|
|
|
|
|
def reshape_tensor(x, heads):
|
|
bs, length, width = x.shape
|
|
|
|
x = x.view(bs, length, heads, -1)
|
|
|
|
x = x.transpose(1, 2)
|
|
|
|
x = x.reshape(bs, heads, length, -1)
|
|
return x
|
|
|
|
|
|
def masked_mean(t, *, dim, mask=None):
|
|
if mask is None:
|
|
return t.mean(dim=dim)
|
|
|
|
denom = mask.sum(dim=dim, keepdim=True)
|
|
mask = rearrange(mask, "b n -> b n 1")
|
|
masked_t = t.masked_fill(~mask, 0.0)
|
|
|
|
return masked_t.sum(dim=dim) / denom.clamp(min=1e-5)
|
|
|
|
|
|
class PerceiverAttention(nn.Module):
|
|
def __init__(self, *, dim, dim_head=64, heads=8):
|
|
super().__init__()
|
|
self.scale = dim_head ** -0.5
|
|
self.dim_head = dim_head
|
|
self.heads = heads
|
|
inner_dim = dim_head * heads
|
|
|
|
self.norm1 = nn.LayerNorm(dim)
|
|
self.norm2 = nn.LayerNorm(dim)
|
|
|
|
self.to_q = nn.Linear(dim, inner_dim, bias=False)
|
|
self.to_kv = nn.Linear(dim, inner_dim * 2, bias=False)
|
|
self.to_out = nn.Linear(inner_dim, dim, bias=False)
|
|
|
|
def forward(self, x, latents):
|
|
"""
|
|
Args:
|
|
x (torch.Tensor): image features
|
|
shape (b, n1, D)
|
|
latent (torch.Tensor): latent features
|
|
shape (b, n2, D)
|
|
"""
|
|
x = self.norm1(x)
|
|
latents = self.norm2(latents)
|
|
|
|
b, l, _ = latents.shape
|
|
|
|
q = self.to_q(latents)
|
|
kv_input = torch.cat((x, latents), dim=-2)
|
|
k, v = self.to_kv(kv_input).chunk(2, dim=-1)
|
|
|
|
q = reshape_tensor(q, self.heads)
|
|
k = reshape_tensor(k, self.heads)
|
|
v = reshape_tensor(v, self.heads)
|
|
|
|
|
|
scale = 1 / math.sqrt(math.sqrt(self.dim_head))
|
|
weight = (q * scale) @ (k * scale).transpose(-2, -1)
|
|
weight = torch.softmax(weight.float(), dim=-1).type(weight.dtype)
|
|
out = weight @ v
|
|
|
|
out = out.permute(0, 2, 1, 3).reshape(b, l, -1)
|
|
|
|
return self.to_out(out)
|
|
|
|
|
|
def FeedForward(dim, mult=4):
|
|
inner_dim = int(dim * mult)
|
|
return nn.Sequential(
|
|
nn.LayerNorm(dim),
|
|
nn.Linear(dim, inner_dim, bias=False),
|
|
nn.GELU(),
|
|
nn.Linear(inner_dim, dim, bias=False),
|
|
)
|
|
|
|
|
|
class AudioProjection(ModelMixin):
|
|
def __init__(
|
|
self,
|
|
dim=1024,
|
|
depth=8,
|
|
dim_head=64,
|
|
heads=16,
|
|
num_queries=8,
|
|
embedding_dim=768,
|
|
output_dim=1024,
|
|
ff_mult=4,
|
|
max_seq_len: int = 257,
|
|
num_latents_mean_pooled: int = 0,
|
|
):
|
|
super().__init__()
|
|
|
|
self.pos_emb = nn.Embedding(max_seq_len, embedding_dim)
|
|
self.latents = nn.Parameter(torch.randn(1, num_queries, dim) / dim ** 0.5)
|
|
|
|
self.proj_in = nn.Linear(embedding_dim, dim)
|
|
|
|
self.proj_out = nn.Linear(dim, output_dim)
|
|
self.norm_out = nn.LayerNorm(output_dim)
|
|
|
|
self.to_latents_from_mean_pooled_seq = (
|
|
nn.Sequential(
|
|
nn.LayerNorm(dim),
|
|
nn.Linear(dim, dim * num_latents_mean_pooled),
|
|
Rearrange("b (n d) -> b n d", n=num_latents_mean_pooled),
|
|
)
|
|
if num_latents_mean_pooled > 0
|
|
else None
|
|
)
|
|
|
|
self.layers = nn.ModuleList([])
|
|
for _ in range(depth):
|
|
self.layers.append(nn.ModuleList([
|
|
PerceiverAttention(dim=dim, dim_head=dim_head, heads=heads),
|
|
FeedForward(dim=dim, mult=ff_mult),
|
|
]))
|
|
|
|
def forward(self, x):
|
|
if self.pos_emb is not None:
|
|
n, device = x.shape[1], x.device
|
|
pos_emb = self.pos_emb(torch.arange(n, device=device))
|
|
x = x + pos_emb
|
|
|
|
latents = self.latents.repeat(x.size(0), 1, 1)
|
|
|
|
x = self.proj_in(x)
|
|
|
|
if self.to_latents_from_mean_pooled_seq:
|
|
meanpooled_seq = masked_mean(x, dim=1, mask=torch.ones(x.shape[:2], device=x.device, dtype=torch.bool))
|
|
meanpooled_latents = self.to_latents_from_mean_pooled_seq(meanpooled_seq)
|
|
latents = torch.cat((meanpooled_latents, latents), dim=-2)
|
|
|
|
for attn, ff in self.layers:
|
|
latents = attn(x, latents) + latents
|
|
latents = ff(latents) + latents
|
|
|
|
latents = self.proj_out(latents)
|
|
return self.norm_out(latents)
|
|
|
