|
import torch |
|
import torch.nn as nn |
|
from functools import partial |
|
|
|
from timm.models.layers import DropPath, to_2tuple, trunc_normal_ |
|
from timm.models.registry import register_model |
|
|
|
import math |
|
|
|
|
|
class MLPLayer(nn.Module): |
|
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) |
|
|
|
def forward(self, x): |
|
x = self.fc1(x) |
|
x = self.act(x) |
|
x = self.drop(x) |
|
x = self.fc2(x) |
|
x = self.drop(x) |
|
return x |
|
|
|
|
|
class Attention(nn.Module): |
|
def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0., sr_ratio=1): |
|
super().__init__() |
|
assert dim % num_heads == 0, f"dim {dim} should be divided by num_heads {num_heads}." |
|
|
|
self.dim = dim |
|
self.num_heads = num_heads |
|
head_dim = dim // num_heads |
|
self.scale = qk_scale or head_dim ** -0.5 |
|
|
|
self.q = nn.Linear(dim, dim, bias=qkv_bias) |
|
self.kv = nn.Linear(dim, dim * 2, bias=qkv_bias) |
|
self.attn_drop = nn.Dropout(attn_drop) |
|
self.proj = nn.Linear(dim, dim) |
|
self.proj_drop = nn.Dropout(proj_drop) |
|
|
|
self.sr_ratio = sr_ratio |
|
if sr_ratio > 1: |
|
self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio) |
|
self.norm = nn.LayerNorm(dim) |
|
|
|
def forward(self, x, H, W): |
|
B, N, C = x.shape |
|
q = self.q(x).reshape(B, N, self.num_heads, C // self.num_heads).permute(0, 2, 1, 3) |
|
|
|
if self.sr_ratio > 1: |
|
x_ = x.permute(0, 2, 1).reshape(B, C, H, W) |
|
x_ = self.sr(x_).reshape(B, C, -1).permute(0, 2, 1) |
|
x_ = self.norm(x_) |
|
kv = self.kv(x_).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4) |
|
else: |
|
kv = self.kv(x).reshape(B, -1, 2, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4) |
|
k, v = kv[0], kv[1] |
|
|
|
attn = (q @ k.transpose(-2, -1)) * self.scale |
|
attn = attn.softmax(dim=-1) |
|
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 |
|
|
|
|
|
class Block(nn.Module): |
|
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., |
|
drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, sr_ratio=1): |
|
super().__init__() |
|
self.norm1 = norm_layer(dim) |
|
self.attn = Attention( |
|
dim, |
|
num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, |
|
attn_drop=attn_drop, proj_drop=drop, sr_ratio=sr_ratio) |
|
|
|
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 = MLPLayer(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop) |
|
|
|
def forward(self, x, H, W): |
|
x = x + self.drop_path(self.attn(self.norm1(x), H, W)) |
|
x = x + self.drop_path(self.mlp(self.norm2(x), H, W)) |
|
return x |
|
|
|
|
|
class OverlapPatchEmbed(nn.Module): |
|
""" Image to Patch Embedding |
|
""" |
|
|
|
def __init__(self, img_size=224, patch_size=7, stride=4, in_channels=3, embed_dim=768): |
|
super().__init__() |
|
img_size = to_2tuple(img_size) |
|
patch_size = to_2tuple(patch_size) |
|
|
|
self.img_size = img_size |
|
self.patch_size = patch_size |
|
self.H, self.W = img_size[0] // patch_size[0], img_size[1] // patch_size[1] |
|
self.num_patches = self.H * self.W |
|
self.proj = nn.Conv2d(in_channels, embed_dim, kernel_size=patch_size, stride=stride, |
|
padding=(patch_size[0] // 2, patch_size[1] // 2)) |
|
self.norm = nn.LayerNorm(embed_dim) |
|
|
|
def forward(self, x): |
|
x = self.proj(x) |
|
_, _, H, W = x.shape |
|
x = x.flatten(2).transpose(1, 2) |
|
x = self.norm(x) |
|
return x, H, W |
|
|
|
|