-
Notifications
You must be signed in to change notification settings - Fork 0
/
resnet_cifar.py
140 lines (109 loc) · 4.47 KB
/
resnet_cifar.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
import sys
import torch.nn as nn
try:
from torch.hub import load_state_dict_from_url
except ImportError:
from torch.utils.model_zoo import load_url as load_state_dict_from_url
from .quantization import *
from functools import partial
from typing import Dict, Type, Any, Callable, Union, List, Optional
cifar10_pretrained_weight_urls = {
'resnet20': 'https://github.com/chenyaofo/pytorch-cifar-models/releases/download/resnet/cifar10_resnet20-4118986f.pt',
'resnet32': 'https://github.com/chenyaofo/pytorch-cifar-models/releases/download/resnet/cifar10_resnet32-ef93fc4d.pt',
'resnet44': 'https://github.com/chenyaofo/pytorch-cifar-models/releases/download/resnet/cifar10_resnet44-2a3cabcb.pt',
'resnet56': 'https://github.com/chenyaofo/pytorch-cifar-models/releases/download/resnet/cifar10_resnet56-187c023a.pt',
}
def conv3x3(in_planes, out_planes, stride=1):
"""3x3 convolution with padding"""
return quan_Conv2d(in_planes, out_planes, kernel_size=3, stride=stride, padding=1, bias=False)
def conv1x1(in_planes, out_planes, stride=1):
"""1x1 convolution"""
return quan_Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, inplanes, planes, stride=1, downsample=None):
super(BasicBlock, self).__init__()
self.conv1 = conv3x3(inplanes, planes, stride)
self.bn1 = nn.BatchNorm2d(planes)
self.relu = nn.ReLU(inplace=True)
self.conv2 = conv3x3(planes, planes)
self.bn2 = nn.BatchNorm2d(planes)
self.downsample = downsample
self.stride = stride
def forward(self, x):
identity = x
out = self.conv1(x)
out = self.bn1(out)
out = self.relu(out)
out = self.conv2(out)
out = self.bn2(out)
if self.downsample is not None:
identity = self.downsample(x)
out += identity
out = self.relu(out)
return out
class CifarResNet(nn.Module):
def __init__(self, block, layers, num_classes=10):
super(CifarResNet, self).__init__()
self.inplanes = 16
self.conv1 = conv3x3(3, 16)
self.bn1 = nn.BatchNorm2d(16)
self.relu = nn.ReLU(inplace=True)
self.layer1 = self._make_layer(block, 16, layers[0])
self.layer2 = self._make_layer(block, 32, layers[1], stride=2)
self.layer3 = self._make_layer(block, 64, layers[2], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = quan_Linear(64 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, quan_Conv2d):
nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
elif isinstance(m, nn.BatchNorm2d):
nn.init.constant_(m.weight, 1)
nn.init.constant_(m.bias, 0)
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
conv1x1(self.inplanes, planes * block.expansion, stride),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
def forward(self, x):
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
def _resnet(
arch: str,
layers: List[int],
model_urls: Dict[str, str],
progress: bool = True,
pretrained: bool = True,
**kwargs: Any
) -> CifarResNet:
model = CifarResNet(BasicBlock, layers, **kwargs)
if pretrained:
pretrained_dict = load_state_dict_from_url(model_urls[arch],
progress=progress)
model_dict = model.state_dict()
pretrained_dict = {
k: v
for k, v in pretrained_dict.items() if k in model_dict
}
model_dict.update(pretrained_dict)
model.load_state_dict(model_dict)
return model
def vanilla_resnet20(num_classes=10):
model = _resnet('resnet20', [3]*3, cifar10_pretrained_weight_urls, )
return model