Source code for mmagic.models.editors.swinir.swinir_rstb
# Copyright (c) OpenMMLab. All rights reserved.
import torch
import torch.nn as nn
import torch.utils.checkpoint as checkpoint
from mmengine.model.weight_init import trunc_normal_
from .swinir_modules import PatchEmbed, PatchUnEmbed
from .swinir_utils import (drop_path, to_2tuple, window_partition,
window_reverse)
[docs]class DropPath(nn.Module):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of
residual blocks)."""
def __init__(self, drop_prob: float = 0., scale_by_keep: bool = True):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
self.scale_by_keep = scale_by_keep
[docs] def forward(self, x):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (B, L, C).
Returns:
Tensor: Forward results.
"""
return drop_path(x, self.drop_prob, self.training, self.scale_by_keep)
[docs]class Mlp(nn.Module):
"""Multilayer Perceptron layer.
Args:
in_features (int): Number of input channels.
hidden_features (int | None, optional): Number of hidden layer
channels. Default: None
out_features (int | None, optional): Number of output channels.
Default: None
act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
drop (float, optional): Dropout ratio of attention weight. Default: 0.0
"""
def __init__(self,
in_features,
hidden_features=None,
out_features=None,
act_layer=nn.GELU,
drop=0.):
super().__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
self.fc1 = nn.Linear(in_features, hidden_features)
self.act = act_layer()
self.fc2 = nn.Linear(hidden_features, out_features)
self.drop = nn.Dropout(drop)
[docs] def forward(self, x):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (B, L, C).
Returns:
Tensor: Forward results.
"""
x = self.fc1(x)
x = self.act(x)
x = self.drop(x)
x = self.fc2(x)
x = self.drop(x)
return x
[docs]class WindowAttention(nn.Module):
r""" Window based multi-head self attention (W-MSA)
module with relative position bias.
It supports both of shifted and non-shifted window.
Args:
dim (int): Number of input channels.
window_size (tuple[int]): The height and width of the window.
num_heads (int): Number of attention heads.
qkv_bias (bool, optional): If True, add a learnable bias to
query, key, value. Default: True
qk_scale (float | None, optional): Override default qk scale
of head_dim ** -0.5 if set
attn_drop (float, optional): Dropout ratio of attention weight.
Default: 0.0
proj_drop (float, optional): Dropout ratio of output. Default: 0.0
"""
def __init__(self,
dim,
window_size,
num_heads,
qkv_bias=True,
qk_scale=None,
attn_drop=0.,
proj_drop=0.):
super().__init__()
self.dim = dim
self.window_size = window_size # Wh, Ww
self.num_heads = num_heads
head_dim = dim // num_heads
self.scale = qk_scale or head_dim**-0.5
# define a parameter table of relative position bias
# 2*Wh-1 * 2*Ww-1, nH
self.relative_position_bias_table = nn.Parameter(
torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1),
num_heads))
# get pair-wise relative position index
# for each token inside the window
coords_h = torch.arange(self.window_size[0])
coords_w = torch.arange(self.window_size[1])
coords = torch.stack(torch.meshgrid([coords_h, coords_w])) # 2, Wh, Ww
coords_flatten = torch.flatten(coords, 1) # 2, Wh*Ww
relative_coords = \
coords_flatten[:, :, None] - coords_flatten[:, None, :]
# Wh*Ww, Wh*Ww, 2
relative_coords = relative_coords.permute(1, 2, 0).contiguous()
# shift to start from 0
relative_coords[:, :, 0] += self.window_size[0] - 1
relative_coords[:, :, 1] += self.window_size[1] - 1
relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
relative_position_index = relative_coords.sum(-1) # Wh*Ww, Wh*Ww
self.register_buffer('relative_position_index',
relative_position_index)
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
self.attn_drop = nn.Dropout(attn_drop)
self.proj = nn.Linear(dim, dim)
self.proj_drop = nn.Dropout(proj_drop)
trunc_normal_(self.relative_position_bias_table, std=.02)
self.softmax = nn.Softmax(dim=-1)
[docs] def forward(self, x, mask=None):
"""
Args:
x: input features with shape of (num_windows*B, N, C)
mask: (0/-inf) mask with shape of
(num_windows, Wh*Ww, Wh*Ww) or None
"""
B_, N, C = x.shape
qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads,
C // self.num_heads).permute(2, 0, 3, 1, 4)
# make torchscript happy (cannot use tensor as tuple)
q, k, v = qkv[0], qkv[1], qkv[2]
q = q * self.scale
attn = (q @ k.transpose(-2, -1))
relative_position_bias = self.relative_position_bias_table[
self.relative_position_index.view(-1)].view(
self.window_size[0] * self.window_size[1],
self.window_size[0] * self.window_size[1],
-1) # Wh*Ww,Wh*Ww,nH
relative_position_bias = relative_position_bias.permute(
2, 0, 1).contiguous() # nH, Wh*Ww, Wh*Ww
attn = attn + relative_position_bias.unsqueeze(0)
if mask is not None:
nW = mask.shape[0]
attn = attn.view(B_ // nW, nW, self.num_heads, N,
N) + mask.unsqueeze(1).unsqueeze(0)
attn = attn.view(-1, self.num_heads, N, N)
attn = self.softmax(attn)
else:
attn = self.softmax(attn)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
f'num_heads={self.num_heads}'
[docs]class SwinTransformerBlock(nn.Module):
r""" Swin Transformer Block.
Args:
dim (int): Number of input channels.
input_resolution (tuple[int]): Input resolution.
num_heads (int): Number of attention heads.
window_size (int): Window size.
shift_size (int): Shift size for SW-MSA.
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
qkv_bias (bool, optional): If True, add a learnable bias
to query, key, value. Default: True
qk_scale (float | None, optional): Override default qk
scale of head_dim ** -0.5 if set.
drop (float, optional): Dropout rate. Default: 0.0
attn_drop (float, optional): Attention dropout rate. Default: 0.0
drop_path (float, optional): Stochastic depth rate. Default: 0.0
act_layer (nn.Module, optional): Activation layer. Default: nn.GELU
norm_layer (nn.Module, optional): Normalization layer.
Default: nn.LayerNorm
"""
def __init__(self,
dim,
input_resolution,
num_heads,
window_size=7,
shift_size=0,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
drop=0.,
attn_drop=0.,
drop_path=0.,
act_layer=nn.GELU,
norm_layer=nn.LayerNorm):
super().__init__()
self.dim = dim
self.input_resolution = input_resolution
self.num_heads = num_heads
self.window_size = window_size
self.shift_size = shift_size
self.mlp_ratio = mlp_ratio
if min(self.input_resolution) <= self.window_size:
# if window size is larger than input resolution,
# we don't partition windows
self.shift_size = 0
self.window_size = min(self.input_resolution)
assert 0 <= self.shift_size < self.window_size, \
'shift_size must in 0-window_size'
self.norm1 = norm_layer(dim)
self.attn = WindowAttention(
dim,
window_size=to_2tuple(self.window_size),
num_heads=num_heads,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
attn_drop=attn_drop,
proj_drop=drop)
self.drop_path = DropPath(
drop_path) if drop_path > 0. else nn.Identity()
self.norm2 = norm_layer(dim)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = Mlp(
in_features=dim,
hidden_features=mlp_hidden_dim,
act_layer=act_layer,
drop=drop)
if self.shift_size > 0:
attn_mask = self.calculate_mask(self.input_resolution)
else:
attn_mask = None
self.register_buffer('attn_mask', attn_mask)
[docs] def calculate_mask(self, x_size):
# calculate attention mask for SW-MSA
"""Calculate attention mask for SW-MSA.
Args:
x_size (tuple[int]): Resolution of input feature.
Returns:
Tensor: Attention mask
"""
H, W = x_size
img_mask = torch.zeros((1, H, W, 1)) # 1 H W 1
h_slices = (slice(0, -self.window_size),
slice(-self.window_size,
-self.shift_size), slice(-self.shift_size, None))
w_slices = (slice(0, -self.window_size),
slice(-self.window_size,
-self.shift_size), slice(-self.shift_size, None))
cnt = 0
for h in h_slices:
for w in w_slices:
img_mask[:, h, w, :] = cnt
cnt += 1
mask_windows = window_partition(
img_mask, self.window_size) # nW, window_size, window_size, 1
mask_windows = mask_windows.view(-1,
self.window_size * self.window_size)
attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
attn_mask = attn_mask.masked_fill(attn_mask != 0,
float(-100.0)).masked_fill(
attn_mask == 0, float(0.0))
return attn_mask
[docs] def forward(self, x, x_size):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (B, L, C).
x_size (tuple[int]): Resolution of input feature.
Returns:
Tensor: Forward results.
"""
H, W = x_size
B, L, C = x.shape
# assert L == H * W, "input feature has wrong size"
shortcut = x
x = self.norm1(x)
x = x.view(B, H, W, C)
# cyclic shift
if self.shift_size > 0:
shifted_x = torch.roll(
x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
else:
shifted_x = x
# partition windows
x_windows = window_partition(
shifted_x, self.window_size) # nW*B, window_size, window_size, C
x_windows = x_windows.view(-1, self.window_size * self.window_size,
C) # nW*B, window_size*window_size, C
# W-MSA/SW-MSA (to be compatible for testing on images
# whose shapes are the multiple of window size
if self.input_resolution == x_size:
attn_windows = self.attn(
x_windows,
mask=self.attn_mask) # nW*B, window_size*window_size, C
else:
attn_windows = self.attn(
x_windows, mask=self.calculate_mask(x_size).to(x.device))
# merge windows
attn_windows = attn_windows.view(-1, self.window_size,
self.window_size, C)
shifted_x = window_reverse(attn_windows, self.window_size, H,
W) # B H' W' C
# reverse cyclic shift
if self.shift_size > 0:
x = torch.roll(
shifted_x,
shifts=(self.shift_size, self.shift_size),
dims=(1, 2))
else:
x = shifted_x
x = x.view(B, H * W, C)
# FFN
x = shortcut + self.drop_path(x)
x = x + self.drop_path(self.mlp(self.norm2(x)))
return x
f'input_resolution={self.input_resolution}, ' \
f'num_heads={self.num_heads}, ' \
f'window_size={self.window_size}, ' \
f'shift_size={self.shift_size}, ' \
f'mlp_ratio={self.mlp_ratio}'
[docs]class BasicLayer(nn.Module):
"""A basic Swin Transformer layer for one stage.
Args:
dim (int): Number of input channels.
input_resolution (tuple[int]): Input resolution.
depth (int): Number of blocks.
num_heads (int): Number of attention heads.
window_size (int): Local window size.
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
qkv_bias (bool, optional): If True, add a learnable bias
to query, key, value. Default: True
qk_scale (float | None, optional): Override default qk
scale of head_dim ** -0.5 if set.
drop (float, optional): Dropout rate. Default: 0.0
attn_drop (float, optional): Attention dropout rate. Default: 0.0
drop_path (float | tuple[float], optional): Stochastic depth rate.
Default: 0.0
norm_layer (nn.Module, optional): Normalization layer.
Default: nn.LayerNorm
downsample (nn.Module | None, optional): Downsample layer at the
end of the layer. Default: None
use_checkpoint (bool): Whether to use checkpointing to save memory.
Default: False.
"""
def __init__(self,
dim,
input_resolution,
depth,
num_heads,
window_size,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
drop=0.,
attn_drop=0.,
drop_path=0.,
norm_layer=nn.LayerNorm,
downsample=None,
use_checkpoint=False):
super().__init__()
self.dim = dim
self.input_resolution = input_resolution
self.depth = depth
self.use_checkpoint = use_checkpoint
# build blocks
self.blocks = nn.ModuleList([
SwinTransformerBlock(
dim=dim,
input_resolution=input_resolution,
num_heads=num_heads,
window_size=window_size,
shift_size=0 if (i % 2 == 0) else window_size // 2,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
drop=drop,
attn_drop=attn_drop,
drop_path=drop_path[i]
if isinstance(drop_path, list) else drop_path,
norm_layer=norm_layer) for i in range(depth)
])
# patch merging layer
if downsample is not None:
self.downsample = downsample(
input_resolution, dim=dim, norm_layer=norm_layer)
else:
self.downsample = None
[docs] def forward(self, x, x_size):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (B, L, C).
x_size (tuple[int]): Resolution of input feature.
Returns:
Tensor: Forward results.
"""
for blk in self.blocks:
if self.use_checkpoint:
x = checkpoint.checkpoint(blk, x, x_size)
else:
x = blk(x, x_size)
if self.downsample is not None:
x = self.downsample(x)
return x
f'input_resolution={self.input_resolution}, ' \
f'depth={self.depth}'
[docs]class RSTB(nn.Module):
"""Residual Swin Transformer Block (RSTB).
Args:
dim (int): Number of input channels.
input_resolution (tuple[int]): Input resolution.
depth (int): Number of blocks.
num_heads (int): Number of attention heads.
window_size (int): Local window size.
mlp_ratio (float): Ratio of mlp hidden dim to embedding dim.
Default: 4.0
qkv_bias (bool, optional): If True, add a learnable bias to
query, key, value. Default: True
qk_scale (float | None, optional): Override default qk scale
of head_dim ** -0.5 if set.
drop (float, optional): Dropout rate. Default: 0.0
attn_drop (float, optional): Attention dropout rate. Default: 0.0
drop_path (float | tuple[float], optional): Stochastic depth rate.
Default: 0.0
norm_layer (nn.Module, optional): Normalization layer.
Default: nn.LayerNorm
downsample (nn.Module | None, optional): Downsample layer at the
end of the layer. Default: None
use_checkpoint (bool): Whether to use checkpointing to save memory.
Default: False.
img_size (int): Input image size. Default: 224
patch_size (int): Patch size. Default: 4
resi_connection (string): The convolutional block before
residual connection. Default: '1conv'
"""
def __init__(self,
dim,
input_resolution,
depth,
num_heads,
window_size,
mlp_ratio=4.,
qkv_bias=True,
qk_scale=None,
drop=0.,
attn_drop=0.,
drop_path=0.,
norm_layer=nn.LayerNorm,
downsample=None,
use_checkpoint=False,
img_size=224,
patch_size=4,
resi_connection='1conv'):
super(RSTB, self).__init__()
self.dim = dim
self.input_resolution = input_resolution
self.residual_group = BasicLayer(
dim=dim,
input_resolution=input_resolution,
depth=depth,
num_heads=num_heads,
window_size=window_size,
mlp_ratio=mlp_ratio,
qkv_bias=qkv_bias,
qk_scale=qk_scale,
drop=drop,
attn_drop=attn_drop,
drop_path=drop_path,
norm_layer=norm_layer,
downsample=downsample,
use_checkpoint=use_checkpoint)
if resi_connection == '1conv':
self.conv = nn.Conv2d(dim, dim, 3, 1, 1)
elif resi_connection == '3conv':
# to save parameters and memory
self.conv = nn.Sequential(
nn.Conv2d(dim, dim // 4, 3, 1, 1),
nn.LeakyReLU(negative_slope=0.2, inplace=True),
nn.Conv2d(dim // 4, dim // 4, 1, 1, 0),
nn.LeakyReLU(negative_slope=0.2, inplace=True),
nn.Conv2d(dim // 4, dim, 3, 1, 1))
self.patch_embed = PatchEmbed(
img_size=img_size,
patch_size=patch_size,
in_chans=0,
embed_dim=dim,
norm_layer=None)
self.patch_unembed = PatchUnEmbed(
img_size=img_size,
patch_size=patch_size,
in_chans=0,
embed_dim=dim,
norm_layer=None)
[docs] def forward(self, x, x_size):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (B, L, C).
x_size (tuple[int]): Resolution of input feature.
Returns:
Tensor: Forward results.
"""
return self.patch_embed(
self.conv(
self.patch_unembed(self.residual_group(x, x_size),
x_size))) + x