forked from lucidrains/vit-pytorch
-
Notifications
You must be signed in to change notification settings - Fork 0
/
mobile_vit.py
252 lines (204 loc) · 7.71 KB
/
mobile_vit.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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
import torch
import torch.nn as nn
from einops import rearrange
from einops.layers.torch import Reduce
# helpers
def conv_1x1_bn(inp, oup):
return nn.Sequential(
nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
nn.SiLU()
)
def conv_nxn_bn(inp, oup, kernel_size=3, stride=1):
return nn.Sequential(
nn.Conv2d(inp, oup, kernel_size, stride, 1, bias=False),
nn.BatchNorm2d(oup),
nn.SiLU()
)
# classes
class PreNorm(nn.Module):
def __init__(self, dim, fn):
super().__init__()
self.norm = nn.LayerNorm(dim)
self.fn = fn
def forward(self, x, **kwargs):
return self.fn(self.norm(x), **kwargs)
class FeedForward(nn.Module):
def __init__(self, dim, hidden_dim, dropout=0.):
super().__init__()
self.net = nn.Sequential(
nn.Linear(dim, hidden_dim),
nn.SiLU(),
nn.Dropout(dropout),
nn.Linear(hidden_dim, dim),
nn.Dropout(dropout)
)
def forward(self, x):
return self.net(x)
class Attention(nn.Module):
def __init__(self, dim, heads=8, dim_head=64, dropout=0.):
super().__init__()
inner_dim = dim_head * heads
self.heads = heads
self.scale = dim_head ** -0.5
self.attend = nn.Softmax(dim=-1)
self.dropout = nn.Dropout(dropout)
self.to_qkv = nn.Linear(dim, inner_dim * 3, bias=False)
self.to_out = nn.Sequential(
nn.Linear(inner_dim, dim),
nn.Dropout(dropout)
)
def forward(self, x):
qkv = self.to_qkv(x).chunk(3, dim=-1)
q, k, v = map(lambda t: rearrange(
t, 'b p n (h d) -> b p h n d', h=self.heads), qkv)
dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale
attn = self.attend(dots)
attn = self.dropout(attn)
out = torch.matmul(attn, v)
out = rearrange(out, 'b p h n d -> b p n (h d)')
return self.to_out(out)
class Transformer(nn.Module):
"""Transformer block described in ViT.
Paper: https://arxiv.org/abs/2010.11929
Based on: https://github.com/lucidrains/vit-pytorch
"""
def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout=0.):
super().__init__()
self.layers = nn.ModuleList([])
for _ in range(depth):
self.layers.append(nn.ModuleList([
PreNorm(dim, Attention(dim, heads, dim_head, dropout)),
PreNorm(dim, FeedForward(dim, mlp_dim, dropout))
]))
def forward(self, x):
for attn, ff in self.layers:
x = attn(x) + x
x = ff(x) + x
return x
class MV2Block(nn.Module):
"""MV2 block described in MobileNetV2.
Paper: https://arxiv.org/pdf/1801.04381
Based on: https://github.com/tonylins/pytorch-mobilenet-v2
"""
def __init__(self, inp, oup, stride=1, expansion=4):
super().__init__()
self.stride = stride
assert stride in [1, 2]
hidden_dim = int(inp * expansion)
self.use_res_connect = self.stride == 1 and inp == oup
if expansion == 1:
self.conv = nn.Sequential(
# dw
nn.Conv2d(hidden_dim, hidden_dim, 3, stride,
1, groups=hidden_dim, bias=False),
nn.BatchNorm2d(hidden_dim),
nn.SiLU(),
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
)
else:
self.conv = nn.Sequential(
# pw
nn.Conv2d(inp, hidden_dim, 1, 1, 0, bias=False),
nn.BatchNorm2d(hidden_dim),
nn.SiLU(),
# dw
nn.Conv2d(hidden_dim, hidden_dim, 3, stride,
1, groups=hidden_dim, bias=False),
nn.BatchNorm2d(hidden_dim),
nn.SiLU(),
# pw-linear
nn.Conv2d(hidden_dim, oup, 1, 1, 0, bias=False),
nn.BatchNorm2d(oup),
)
def forward(self, x):
out = self.conv(x)
if self.use_res_connect:
out = out + x
return out
class MobileViTBlock(nn.Module):
def __init__(self, dim, depth, channel, kernel_size, patch_size, mlp_dim, dropout=0.):
super().__init__()
self.ph, self.pw = patch_size
self.conv1 = conv_nxn_bn(channel, channel, kernel_size)
self.conv2 = conv_1x1_bn(channel, dim)
self.transformer = Transformer(dim, depth, 4, 8, mlp_dim, dropout)
self.conv3 = conv_1x1_bn(dim, channel)
self.conv4 = conv_nxn_bn(2 * channel, channel, kernel_size)
def forward(self, x):
y = x.clone()
# Local representations
x = self.conv1(x)
x = self.conv2(x)
# Global representations
_, _, h, w = x.shape
x = rearrange(x, 'b d (h ph) (w pw) -> b (ph pw) (h w) d',
ph=self.ph, pw=self.pw)
x = self.transformer(x)
x = rearrange(x, 'b (ph pw) (h w) d -> b d (h ph) (w pw)',
h=h//self.ph, w=w//self.pw, ph=self.ph, pw=self.pw)
# Fusion
x = self.conv3(x)
x = torch.cat((x, y), 1)
x = self.conv4(x)
return x
class MobileViT(nn.Module):
"""MobileViT.
Paper: https://arxiv.org/abs/2110.02178
Based on: https://github.com/chinhsuanwu/mobilevit-pytorch
"""
def __init__(
self,
image_size,
dims,
channels,
num_classes,
expansion=4,
kernel_size=3,
patch_size=(2, 2),
depths=(2, 4, 3)
):
super().__init__()
assert len(dims) == 3, 'dims must be a tuple of 3'
assert len(depths) == 3, 'depths must be a tuple of 3'
ih, iw = image_size
ph, pw = patch_size
assert ih % ph == 0 and iw % pw == 0
init_dim, *_, last_dim = channels
self.conv1 = conv_nxn_bn(3, init_dim, stride=2)
self.stem = nn.ModuleList([])
self.stem.append(MV2Block(channels[0], channels[1], 1, expansion))
self.stem.append(MV2Block(channels[1], channels[2], 2, expansion))
self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
self.stem.append(MV2Block(channels[2], channels[3], 1, expansion))
self.trunk = nn.ModuleList([])
self.trunk.append(nn.ModuleList([
MV2Block(channels[3], channels[4], 2, expansion),
MobileViTBlock(dims[0], depths[0], channels[5],
kernel_size, patch_size, int(dims[0] * 2))
]))
self.trunk.append(nn.ModuleList([
MV2Block(channels[5], channels[6], 2, expansion),
MobileViTBlock(dims[1], depths[1], channels[7],
kernel_size, patch_size, int(dims[1] * 4))
]))
self.trunk.append(nn.ModuleList([
MV2Block(channels[7], channels[8], 2, expansion),
MobileViTBlock(dims[2], depths[2], channels[9],
kernel_size, patch_size, int(dims[2] * 4))
]))
self.to_logits = nn.Sequential(
conv_1x1_bn(channels[-2], last_dim),
Reduce('b c h w -> b c', 'mean'),
nn.Linear(channels[-1], num_classes, bias=False)
)
def forward(self, x):
x = self.conv1(x)
for conv in self.stem:
x = conv(x)
for conv, attn in self.trunk:
x = conv(x)
x = attn(x)
return self.to_logits(x)