Spaces:
Running on Zero
Running on Zero
| from abc import abstractmethod | |
| import math | |
| import numpy as np | |
| import torch as th | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| from refnet.ldm.util import ( | |
| conv_nd, | |
| linear, | |
| avg_pool_nd, | |
| zero_module, | |
| normalization, | |
| timestep_embedding, | |
| ) | |
| from refnet.util import checkpoint_wrapper | |
| # dummy replace | |
| def convert_module_to_f16(x): | |
| pass | |
| def convert_module_to_f32(x): | |
| pass | |
| ## go | |
| class AttentionPool2d(nn.Module): | |
| """ | |
| Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py | |
| """ | |
| def __init__( | |
| self, | |
| spacial_dim: int, | |
| embed_dim: int, | |
| num_heads_channels: int, | |
| output_dim: int = None, | |
| ): | |
| super().__init__() | |
| self.positional_embedding = nn.Parameter(th.randn(embed_dim, spacial_dim ** 2 + 1) / embed_dim ** 0.5) | |
| self.qkv_proj = conv_nd(1, embed_dim, 3 * embed_dim, 1) | |
| self.c_proj = conv_nd(1, embed_dim, output_dim or embed_dim, 1) | |
| self.num_heads = embed_dim // num_heads_channels | |
| self.attention = QKVAttention(self.num_heads) | |
| def forward(self, x): | |
| b, c, *_spatial = x.shape | |
| x = x.reshape(b, c, -1) # NC(HW) | |
| x = th.cat([x.mean(dim=-1, keepdim=True), x], dim=-1) # NC(HW+1) | |
| x = x + self.positional_embedding[None, :, :].to(x.dtype) # NC(HW+1) | |
| x = self.qkv_proj(x) | |
| x = self.attention(x) | |
| x = self.c_proj(x) | |
| return x[:, :, 0] | |
| class TimestepBlock(nn.Module): | |
| """ | |
| Any module where forward() takes timestep embeddings as a second argument. | |
| """ | |
| def forward(self, x, emb): | |
| """ | |
| Apply the module to `x` given `emb` timestep embeddings. | |
| """ | |
| class Upsample(nn.Module): | |
| """ | |
| An upsampling layer with an optional convolution. | |
| :param channels: channels in the inputs and outputs. | |
| :param use_conv: a bool determining if a convolution is applied. | |
| :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then | |
| upsampling occurs in the inner-two dimensions. | |
| """ | |
| def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1): | |
| super().__init__() | |
| self.channels = channels | |
| self.out_channels = out_channels or channels | |
| self.use_conv = use_conv | |
| self.dims = dims | |
| if use_conv: | |
| self.conv = conv_nd(dims, self.channels, self.out_channels, 3, padding=padding) | |
| def forward(self, x): | |
| assert x.shape[1] == self.channels | |
| if self.dims == 3: | |
| x = F.interpolate( | |
| x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest" | |
| ) | |
| else: | |
| x = F.interpolate(x, scale_factor=2, mode="nearest") | |
| if self.use_conv: | |
| x = self.conv(x) | |
| return x | |
| class TransposedUpsample(nn.Module): | |
| 'Learned 2x upsampling without padding' | |
| def __init__(self, channels, out_channels=None, ks=5): | |
| super().__init__() | |
| self.channels = channels | |
| self.out_channels = out_channels or channels | |
| self.up = nn.ConvTranspose2d(self.channels,self.out_channels,kernel_size=ks,stride=2) | |
| def forward(self,x): | |
| return self.up(x) | |
| class Downsample(nn.Module): | |
| """ | |
| A downsampling layer with an optional convolution. | |
| :param channels: channels in the inputs and outputs. | |
| :param use_conv: a bool determining if a convolution is applied. | |
| :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then | |
| downsampling occurs in the inner-two dimensions. | |
| """ | |
| def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1): | |
| super().__init__() | |
| self.channels = channels | |
| self.out_channels = out_channels or channels | |
| self.use_conv = use_conv | |
| self.dims = dims | |
| stride = 2 if dims != 3 else (1, 2, 2) | |
| if use_conv: | |
| self.op = conv_nd( | |
| dims, self.channels, self.out_channels, 3, stride=stride, padding=padding | |
| ) | |
| else: | |
| assert self.channels == self.out_channels | |
| self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride) | |
| def forward(self, x): | |
| assert x.shape[1] == self.channels | |
| return self.op(x) | |
| class ResBlock(TimestepBlock): | |
| """ | |
| A residual block that can optionally change the number of channels. | |
| :param channels: the number of input channels. | |
| :param emb_channels: the number of timestep embedding channels. | |
| :param dropout: the rate of dropout. | |
| :param out_channels: if specified, the number of out channels. | |
| :param use_conv: if True and out_channels is specified, use a spatial | |
| convolution instead of a smaller 1x1 convolution to change the | |
| channels in the skip connection. | |
| :param dims: determines if the signal is 1D, 2D, or 3D. | |
| :param use_checkpoint: if True, use gradient checkpointing on this module. | |
| :param up: if True, use this block for upsampling. | |
| :param down: if True, use this block for downsampling. | |
| """ | |
| def __init__( | |
| self, | |
| channels, | |
| emb_channels, | |
| dropout, | |
| out_channels=None, | |
| use_conv=False, | |
| use_scale_shift_norm=False, | |
| dims=2, | |
| use_checkpoint=False, | |
| up=False, | |
| down=False, | |
| ): | |
| super().__init__() | |
| self.channels = channels | |
| self.emb_channels = emb_channels | |
| self.dropout = dropout | |
| self.out_channels = out_channels or channels | |
| self.use_conv = use_conv | |
| self.checkpoint = use_checkpoint | |
| self.use_scale_shift_norm = use_scale_shift_norm | |
| self.in_layers = nn.Sequential( | |
| normalization(channels), | |
| nn.SiLU(), | |
| conv_nd(dims, channels, self.out_channels, 3, padding=1), | |
| ) | |
| self.updown = up or down | |
| if up: | |
| self.h_upd = Upsample(channels, False, dims) | |
| self.x_upd = Upsample(channels, False, dims) | |
| elif down: | |
| self.h_upd = Downsample(channels, False, dims) | |
| self.x_upd = Downsample(channels, False, dims) | |
| else: | |
| self.h_upd = self.x_upd = nn.Identity() | |
| self.emb_layers = nn.Sequential( | |
| nn.SiLU(), | |
| linear( | |
| emb_channels, | |
| 2 * self.out_channels if use_scale_shift_norm else self.out_channels, | |
| ), | |
| ) | |
| self.out_layers = nn.Sequential( | |
| normalization(self.out_channels), | |
| nn.SiLU(), | |
| nn.Dropout(p=dropout), | |
| zero_module( | |
| conv_nd(dims, self.out_channels, self.out_channels, 3, padding=1) | |
| ), | |
| ) | |
| if self.out_channels == channels: | |
| self.skip_connection = nn.Identity() | |
| elif use_conv: | |
| self.skip_connection = conv_nd( | |
| dims, channels, self.out_channels, 3, padding=1 | |
| ) | |
| else: | |
| self.skip_connection = conv_nd(dims, channels, self.out_channels, 1) | |
| def forward(self, x, emb): | |
| if self.updown: | |
| in_rest, in_conv = self.in_layers[:-1], self.in_layers[-1] | |
| h = in_rest(x) | |
| h = self.h_upd(h) | |
| x = self.x_upd(x) | |
| h = in_conv(h) | |
| else: | |
| h = self.in_layers(x) | |
| emb_out = self.emb_layers(emb).type(h.dtype) | |
| while len(emb_out.shape) < len(h.shape): | |
| emb_out = emb_out[..., None] | |
| if self.use_scale_shift_norm: | |
| out_norm, out_rest = self.out_layers[0], self.out_layers[1:] | |
| scale, shift = th.chunk(emb_out, 2, dim=1) | |
| h = out_norm(h) * (1 + scale) + shift | |
| h = out_rest(h) | |
| else: | |
| h = h + emb_out | |
| h = self.out_layers(h) | |
| return self.skip_connection(x) + h | |
| class AttentionBlock(nn.Module): | |
| """ | |
| An attention block that allows spatial positions to attend to each other. | |
| Originally ported from here, but adapted to the N-d case. | |
| https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/models/unet.py#L66. | |
| """ | |
| def __init__( | |
| self, | |
| channels, | |
| num_heads=1, | |
| num_head_channels=-1, | |
| use_checkpoint=False, | |
| use_new_attention_order=False, | |
| ): | |
| super().__init__() | |
| self.channels = channels | |
| if num_head_channels == -1: | |
| self.num_heads = num_heads | |
| else: | |
| assert ( | |
| channels % num_head_channels == 0 | |
| ), f"q,k,v channels {channels} is not divisible by num_head_channels {num_head_channels}" | |
| self.num_heads = channels // num_head_channels | |
| self.use_checkpoint = use_checkpoint | |
| self.norm = normalization(channels) | |
| self.qkv = conv_nd(1, channels, channels * 3, 1) | |
| if use_new_attention_order: | |
| # split qkv before split heads | |
| self.attention = QKVAttention(self.num_heads) | |
| else: | |
| # split heads before split qkv | |
| self.attention = QKVAttentionLegacy(self.num_heads) | |
| self.proj_out = zero_module(conv_nd(1, channels, channels, 1)) | |
| def forward(self, x): | |
| b, c, *spatial = x.shape | |
| x = x.reshape(b, c, -1) | |
| qkv = self.qkv(self.norm(x)) | |
| h = self.attention(qkv) | |
| h = self.proj_out(h) | |
| return (x + h).reshape(b, c, *spatial) | |
| def count_flops_attn(model, _x, y): | |
| """ | |
| A counter for the `thop` package to count the operations in an | |
| attention operation. | |
| Meant to be used like: | |
| macs, params = thop.profile( | |
| model, | |
| inputs=(inputs, timestamps), | |
| custom_ops={QKVAttention: QKVAttention.count_flops}, | |
| ) | |
| """ | |
| b, c, *spatial = y[0].shape | |
| num_spatial = int(np.prod(spatial)) | |
| # We perform two matmuls with the same number of ops. | |
| # The first computes the weight matrix, the second computes | |
| # the combination of the value vectors. | |
| matmul_ops = 2 * b * (num_spatial ** 2) * c | |
| model.total_ops += th.DoubleTensor([matmul_ops]) | |
| class QKVAttentionLegacy(nn.Module): | |
| """ | |
| A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping | |
| """ | |
| def __init__(self, n_heads): | |
| super().__init__() | |
| self.n_heads = n_heads | |
| def forward(self, qkv): | |
| """ | |
| Apply QKV attention. | |
| :param qkv: an [N x (H * 3 * 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.reshape(bs * self.n_heads, ch * 3, length).split(ch, dim=1) | |
| scale = 1 / math.sqrt(math.sqrt(ch)) | |
| weight = th.einsum( | |
| "bct,bcs->bts", q * scale, k * scale | |
| ) # 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) | |
| return a.reshape(bs, -1, length) | |
| def count_flops(model, _x, y): | |
| return count_flops_attn(model, _x, y) | |
| 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 | |
| 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) | |
| def count_flops(model, _x, y): | |
| return count_flops_attn(model, _x, y) | |
| class Timestep(nn.Module): | |
| def __init__(self, dim): | |
| super().__init__() | |
| self.dim = dim | |
| def forward(self, t): | |
| return timestep_embedding(t, self.dim) |