171 lines
6.4 KiB
Python
171 lines
6.4 KiB
Python
|
import torch
|
||
|
|
import torch.nn as nn
|
||
|
|
import torch.nn.functional as F
|
||
|
|
|
||
|
|
def to_2tuple(x):
|
||
|
|
return tuple([x] * 2)
|
||
|
|
|
||
|
|
class Identity(nn.Module):
|
||
|
|
def __init__(self):
|
||
|
|
super().__init__()
|
||
|
|
|
||
|
|
def forward(self, input):
|
||
|
|
return input
|
||
|
|
|
||
|
|
class PathchEmbed(nn.Module):
|
||
|
|
def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768):
|
||
|
|
super().__init__()
|
||
|
|
img_size = to_2tuple(img_size)
|
||
|
|
patch_size = to_2tuple(patch_size)
|
||
|
|
num_patches = (img_size[1] // patch_size[1]) * (img_size[0] // patch_size[0])
|
||
|
|
self.img_size = img_size
|
||
|
|
self.patch_size = patch_size
|
||
|
|
self.num_patches = num_patches
|
||
|
|
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size[0], stride=patch_size[0])
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
B, C, H, W = x.shape
|
||
|
|
x = self.proj(x).flatten(2).permute(0, 2, 1)
|
||
|
|
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.):
|
||
|
|
super().__init__()
|
||
|
|
self.num_heads = num_heads
|
||
|
|
head_dim = dim // num_heads
|
||
|
|
self.scale = qk_scale or head_dim ** -0.5
|
||
|
|
|
||
|
|
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)
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
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)
|
||
|
|
q, k, v = qkv[0], qkv[1], qkv[2]
|
||
|
|
attn = (q.matmul(k.permute(0, 1, 3, 2))) * self.scale
|
||
|
|
attn = F.softmax(attn, dim=1)
|
||
|
|
attn = self.attn_drop(attn)
|
||
|
|
x = (attn.matmul(v)).permute(0, 2, 1, 3).reshape(B, N, C)
|
||
|
|
x = self.proj(x)
|
||
|
|
x = self.proj_drop(x)
|
||
|
|
return x
|
||
|
|
|
||
|
|
class Mlp(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
|
||
|
|
|
||
|
|
def drop_path(x, drop_prob: float = 0., training: bool = False):
|
||
|
|
if drop_prob == 0. or not training:
|
||
|
|
return x
|
||
|
|
keep_prob = 1 - drop_prob
|
||
|
|
shape = (x.shape[0],) + (1,) * (x.ndim - 1)
|
||
|
|
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
|
||
|
|
random_tensor.floor_()
|
||
|
|
output = x.div(keep_prob) * random_tensor
|
||
|
|
return output
|
||
|
|
|
||
|
|
|
||
|
|
class DropPath(nn.Module):
|
||
|
|
def __init__(self, drop_prob=None):
|
||
|
|
super(DropPath, self).__init__()
|
||
|
|
self.drop_prob = drop_prob
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
return drop_path(x, self.drop_prob, self.training)
|
||
|
|
|
||
|
|
class BasicBlock(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', epsilon=1e-5):
|
||
|
|
super().__init__()
|
||
|
|
self.norm1 = eval(norm_layer)(dim, eps=epsilon)
|
||
|
|
self.attn = Attention(dim=dim, 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 Identity()
|
||
|
|
self.norm2 = eval(norm_layer)(dim, eps=epsilon)
|
||
|
|
mlp_hidden_dim = int(dim * mlp_ratio)
|
||
|
|
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
x = x + self.drop_path(self.attn(self.norm1(x)))
|
||
|
|
x = x + self.drop_path(self.mlp(self.norm2(x)))
|
||
|
|
return x
|
||
|
|
|
||
|
|
def truncated_normal_(tensor,mean=0,std=0.09):
|
||
|
|
with torch.no_grad():
|
||
|
|
size = tensor.shape
|
||
|
|
tmp = tensor.new_empty(size+(4,)).normal_()
|
||
|
|
valid = (tmp < 2) & (tmp > -2)
|
||
|
|
ind = valid.max(-1, keepdim=True)[1]
|
||
|
|
tensor.data.copy_(tmp.gather(-1, ind).squeeze(-1))
|
||
|
|
tensor.data.mul_(std).add_(mean)
|
||
|
|
return tensor
|
||
|
|
|
||
|
|
class VisionTransformer(nn.Module):
|
||
|
|
def __init__(self, img_size=224, patch_size=16, in_chans=3, class_dim=1000,
|
||
|
|
embed_dim=768, depth=12, num_heads=12, mlp_ratio=4, qkv_bias=False,
|
||
|
|
qk_scale=None, drop_rate=0., attn_drop_rate=0., drop_path_rate=0.,
|
||
|
|
norm_layer='nn.LayerNorm', epsilon=1e-5, **args):
|
||
|
|
super().__init__()
|
||
|
|
self.class_dim = class_dim
|
||
|
|
self.patch_embed = PathchEmbed(img_size=img_size, patch_size=patch_size,
|
||
|
|
in_chans=in_chans,embed_dim=embed_dim)
|
||
|
|
num_patches = self.patch_embed.num_patches
|
||
|
|
|
||
|
|
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
|
||
|
|
self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
|
||
|
|
self.pos_drop = nn.Dropout(p=drop_rate)
|
||
|
|
|
||
|
|
dpr = [x for x in torch.linspace(0, drop_path_rate, depth)]
|
||
|
|
|
||
|
|
self.blocks = nn.ModuleList([
|
||
|
|
BasicBlock(
|
||
|
|
dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias,
|
||
|
|
drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[i], norm_layer=norm_layer,
|
||
|
|
epsilon=epsilon) for i in range(depth)
|
||
|
|
])
|
||
|
|
self.norm = eval(norm_layer)(embed_dim, eps=epsilon)
|
||
|
|
self.head = nn.Linear(embed_dim, class_dim) if class_dim > 0 else Identity()
|
||
|
|
|
||
|
|
truncated_normal_(tensor=self.pos_embed)
|
||
|
|
truncated_normal_(tensor=self.cls_token)
|
||
|
|
self.apply(self._init_weights)
|
||
|
|
|
||
|
|
def _init_weights(self, m):
|
||
|
|
if isinstance(m, nn.Linear):
|
||
|
|
truncated_normal_(m.weight)
|
||
|
|
if isinstance(m, nn.Linear) and m.bias is not None:
|
||
|
|
nn.init.constant_(m.bias, 0)
|
||
|
|
elif isinstance(m, nn.LayerNorm):
|
||
|
|
nn.init.constant_(m.bias, 0)
|
||
|
|
nn.init.constant_(m.weight, 1)
|
||
|
|
|
||
|
|
def forward_features(self, x):
|
||
|
|
B = x.shape[0]
|
||
|
|
x = self.patch_embed(x)
|
||
|
|
cls_tokens = self.cls_token.expand(B, -1, -1)
|
||
|
|
x = torch.cat([cls_tokens, x], axis=1)
|
||
|
|
x = x + self.pos_embed
|
||
|
|
x = self.pos_drop(x)
|
||
|
|
for blk in self.blocks:
|
||
|
|
x = blk(x)
|
||
|
|
x = self.norm(x)
|
||
|
|
return x[:,0]
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
x = self.forward_features(x)
|
||
|
|
x = self.head(x)
|
||
|
|
return x
|