-
Notifications
You must be signed in to change notification settings - Fork 0
/
task2.py
164 lines (121 loc) · 4.97 KB
/
task2.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
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
import time
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(device)
num_epochs = 11
learning_rate = 0.1
num_classes = 10
batch_size = 128
#model
model_name = "CI"
#data
transform_train = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
transforms.RandomHorizontalFlip(),
transforms.RandomCrop(32, padding=4, padding_mode='reflect'),
])
transform_test = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform_train)
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform_test)
train_loader = torch.utils.data.DataLoader(trainset, batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(testset, batch_size=batch_size,
shuffle=False)
#--------------- Model
class BasicBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion*planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(self.expansion*planes)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = F.relu(out)
return out
class ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=10):
super(ResNet, self).__init__() # Correctly call the parent class constructor
self.in_planes = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.linear = nn.Linear(512*block.expansion, num_classes)
def _make_layer(self, block, planes, num_blocks, stride):
strides = [stride] + [1]*(num_blocks-1)
layers = []
for stride in strides:
layers.append(block(self.in_planes, planes, stride))
self.in_planes = planes * block.expansion
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = F.avg_pool2d(out, 4)
out = out.view(out.size(0), -1)
out = self.linear(out)
return out
def ResNet18():
return ResNet(BasicBlock, [2, 2, 2, 2])
def ResNet34():
return ResNet(BasicBlock, [3, 4, 6, 3])
model = ResNet18()
model = model.to(device=device)
#print(model)
critereon = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate, momentum=0.9, weight_decay=5e-4)
total_step = len(train_loader)
scheduler = torch.optim.lr_scheduler.OneCycleLR(optimizer, max_lr=learning_rate, epochs=num_epochs, steps_per_epoch=len(train_loader))
# ... (Previous code)
#running the model
print("Now training")
start = time.time() # Time measurement
n_total_steps = len(train_loader)
for i in range(num_epochs):
model.train()
total_correct = 0
total_samples = 0
for j, (images, labels) in enumerate(train_loader):
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
loss = critereon(outputs, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
scheduler.step()
# Compute batch accuracy
_, predicted = torch.max(outputs, 1)
total_samples += labels.size(0)
total_correct += (predicted == labels).sum().item()
# Print batch accuracy
batch_accuracy = 100 * total_correct / total_samples
print(f'Epoch [{i+1}/{num_epochs}], Step [{j+1}/{total_step}], Batch Accuracy: {batch_accuracy:.2f}%')
end = time.time()
elapsed = end-start
print(elapsed)
#torch.save(model.state_dict(), path)