-
Notifications
You must be signed in to change notification settings - Fork 1
/
vit_1126.py
189 lines (159 loc) · 6.02 KB
/
vit_1126.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
"""
DateTime: 2021.11.26
Written By: Dr. Zhu
Recorded By: Hatimwen
"""
import paddle
import paddle.nn as nn
paddle.set_device('cpu')
class Identity(nn.Layer):
def __init__(self):
super(Identity, self).__init__()
def forward(self, x):
return x
class Mlp(nn.Layer):
def __init__(self, embed_dim, mlp_ratio, dropout=0.):
super().__init__()
self.fc1 = nn.Linear(embed_dim, int(embed_dim * mlp_ratio))
self.fc2 = nn.Linear(int(embed_dim * mlp_ratio), embed_dim)
self.act = nn.GELU()
self.dropout = nn.Dropout(dropout)
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.dropout(x)
x = self.fc2(x)
x = self.dropout(x)
return x
class PatchEmbedding(nn.Layer):
def __init__(self, image_size=224, patch_size=16, in_channels=3, embed_dim=768, dropout=0.):
super().__init__()
n_patches = (image_size // patch_size) * (image_size // patch_size)
self.patch_embedding = nn.Conv2D(in_channels=in_channels,
out_channels=embed_dim,
kernel_size=patch_size,
stride=patch_size)
self.class_token = paddle.create_parameter(
shape=[1, 1, embed_dim],
dtype='float32',
default_initializer=paddle.nn.initializer.Constant(0.))
self.position_embedding = paddle.create_parameter(
shape=[1, n_patches+1, embed_dim],
dtype='float32',
default_initializer=nn.initializer.TruncatedNormal(std=.02))
self.dropout = nn.Dropout(dropout)
def forward(self, x):
# [n, c, h, w]
class_tokens = self.class_token.expand([x.shape[0], -1, -1])
# class_tokens = self.class_token.expand([x.shape[0], 1, self.embed_dim]) # for batch
x = self.patch_embedding(x) #[n, embed_dim, h', w']
x = x.flatten(2) # [n, embed_dim, h' * w']
x = x.transpose([0, 2, 1]) # [n, h' * w, embed_dim]
x = paddle.concat([class_tokens, x], axis=1)
x = x + self.position_embedding
x = self.dropout(x)
return x
class Attention(nn.Layer):
"""multi-head self attention"""
def __init__(self, embed_dim, num_heads, qkv_bias=True, dropout=0., attention_dropout=0.):
super().__init__()
self.num_heads = num_heads
self.head_dim = int(embed_dim / num_heads)
self.all_head_dim = self.head_dim * num_heads
self.scale = self.head_dim ** -0.5
self.qkv = nn.Linear(embed_dim,
self.all_head_dim * 3)
self.proj = nn.Linear(self.all_head_dim, embed_dim)
self.dropout = nn.Dropout(dropout)
self.attention_dropout = nn.Dropout(attention_dropout)
self.softmax = nn.Softmax(axis=-1)
def transpose_multi_head(self, x):
# N: num_patches
# x: [B, N, all_head_dim]
new_shape = x.shape[:-1] + [self.num_heads, self.head_dim]
x = x.reshape(new_shape)
# x: [B, N, num_heads, head_dim]
x = x.transpose([0, 2, 1, 3])
# x: [B, num_heads, N, head_dim]
return x
def forward(self, x):
B, N, _ = x.shape
qkv = self.qkv(x).chunk(3, -1)
# [B, N, all_head_dim] * 3
q, k, v = map(self.transpose_multi_head, qkv)
# q, k, v: [B, num_heads, N, head_dim]
attn = paddle.matmul(q, k, transpose_y=True) # q * k^T
attn = self.scale * attn
attn = self.softmax(attn)
attn = self.attention_dropout(attn)
# attn :[B, num_heads, N, N]
out = paddle.matmul(attn, v) # softmax(scale(q * k^T)) * v
out = out.transpose([0, 2, 1, 3])
# out: [B, N, num_heads, head_dim]
out = out.reshape([B, N, -1])
out = self.proj(out)
out = self.dropout(out)
return out
class EncoderLayer(nn.Layer):
def __init__(self, embed_dim=768, num_heads=4, qkv_bias=True, mlp_ratio=40, dropout=0., attention_dropout=0.):
super().__init__()
self.attn_norm = nn.LayerNorm(embed_dim)
self.attn = Attention(embed_dim, num_heads)
self.mlp_norm = nn.LayerNorm(embed_dim)
self.mlp = Mlp(embed_dim, mlp_ratio)
def forward(self, x):
h = x # residual
x = self.attn_norm(x)
x = self.attn(x)
x = x + h
h = x
x = self.mlp_norm(x)
x = self.mlp(x)
x = x + h
return x
class Encoder(nn.Layer):
def __init__(self, embed_dim, depth):
super().__init__()
layer_list = []
for i in range(depth):
encoder_layer = EncoderLayer()
layer_list.append(encoder_layer)
self.layers = nn.LayerList(layer_list)
self.norm = nn.LayerNorm(embed_dim)
def forward(self, x):
for layer in self.layers:
x = layer(x)
x = self.norm(x)
return x
class VisualTransformer(nn.Layer):
def __init__(self,
image_size=224,
patch_size=16,
in_channels=3,
num_classes=1000,
embed_dim=768,
depth=3,
num_heads=8,
mlp_ratio=4,
qkv_bias=True,
dropout=0.,
attention_dropout=0.,
droppath=0.):
super().__init__()
self.patch_embedding = PatchEmbedding(image_size, patch_size, in_channels, embed_dim)
self.encoder = Encoder(embed_dim, depth)
self.classifier = nn.Linear(embed_dim, num_classes)
def forward(self, x):
# x: [N, C, H, W]
x = self.patch_embedding(x) # [N, embed_dim, h', w']
# x = x.flatten(2) # [N, embed_dim, h' * w'] h' * w' = num_patches
# x = x.transpose([0, 2, 1]) # [N, num_patches, embed_dim]
x = self.encoder(x)
x = self.classifier(x[:, 0])
return x
def main():
vit = VisualTransformer()
print(vit)
paddle.summary(vit, input_size=(4, 3, 224, 224))
if __name__ == '__main__':
main()